refactor folder structure and update prompt

Author: jungs1

MANIFEST.in

@@ -1 +1 @@
-include src/mutahunter/core/pilot/aider/queries/*.scm
+include src/mutahunter/core/queries/*.scm

README.md

@@ -30,7 +30,7 @@ Mutahunter uses LLM models to inject context-aware faults into your codebase. Th
 
 ## Features
 
-- **Extreme Mutation Testing:** Leverages language agnostic [TreeSitter](https://tree-sitter.github.io/) parser to apply extreme mutations to the codebase without using LLMs. [Research](https://arxiv.org/abs/2103.08480) shows that this approach is effective at detecting pseudo-tested methods with significantly lower computational cost. Currently supports Python, Java, JavaScript, and Go. Check the [scheme files](/src/mutahunter/core/pilot/aider/queries/) to see the supported operators. We welcome contributions to add more operators and languages.
+- **Extreme Mutation Testing:** Leverages language agnostic [TreeSitter](https://tree-sitter.github.io/) parser to apply extreme mutations to the codebase without using LLMs. [Research](https://arxiv.org/abs/2103.08480) shows that this approach is effective at detecting pseudo-tested methods with significantly lower computational cost. Currently supports Python, Java, JavaScript, and Go. Check the [scheme files](/src/mutahunter/core/queries/) to see the supported operators. We welcome contributions to add more operators and languages.
 - **LLM Context-aware Mutations:** Utilizes LLM models to generate context-aware mutants. [Research](https://arxiv.org/abs/2406.09843) indicates that LLM-generated mutants have higher fault detection potential, fewer equivalent mutants, and higher coupling and semantic similarity to real faults. It uses a map of your entire git repository to generate contextually relevant mutants using [aider's repomap](https://aider.chat/docs/repomap.html). Supports self-hosted LLMs, Anthropic, OpenAI, and any LLM models via [LiteLLM](https://github.com/BerriAI/litellm).
 - **Change-Based Testing:** Runs mutation tests on modified files and lines based on the latest commit or pull request changes, ensuring that only relevant parts of the code are tested.
 - **Language Agnostic:** Compatible with languages that provide coverage reports in Cobertura XML, Jacoco XML, and lcov formats. Extensible to additional languages and testing frameworks.
@@ -172,7 +172,6 @@ jobs:
 
 Help us improve Mutahunter and get rewarded! We have a cash bounty program to incentivize contributions to the project. Check out the [bounty board](https://docs.google.com/spreadsheets/d/1cT2_O55m5txrUgZV81g1gtqE_ZDu9LlzgbpNa_HIisc/edit?gid=0#gid=0) to see the available bounties and claim one today!
 
-
 ## Acknowledgements
 
 Mutahunter makes use of the following open-source libraries:

pyproject.toml

@@ -25,12 +25,10 @@ dependencies = [
     'scipy',
     'setuptools',
     'jinja2',
-    'litellm'
+    'litellm',
 ]
 
-authors = [
-    { name = "Steven Jung", email = "[email protected]" },
-]
+authors = [{ name = "Steven Jung", email = "[email protected]" }]
 
 [project.optional-dependencies]
 dev = ['isort', 'black']
@@ -40,4 +38,4 @@ testing = ['pytest']
 mutahunter = "mutahunter.main:run"
 
 [tool.setuptools.package-data]
-mutahunter = ['src/mutahunter/core/pilot/aider/queries/*.scm']
+mutahunter = ['src/mutahunter/core/queries/*.scm']

src/mutahunter/core/analyzer.py

@@ -334,7 +334,7 @@ def _load_query_scm(self, lang: str) -> str:
         """
         try:
             scm_fname = resources.files(__package__).joinpath(
-                "pilot", "aider", "queries", f"tree-sitter-{lang}-tags.scm"
+                "queries", f"tree-sitter-{lang}-tags.scm"
             )
         except KeyError:
             return ""

src/mutahunter/core/mutator.py

@@ -6,8 +6,8 @@
 from jinja2 import Template
 
 from mutahunter.core.logger import logger
-from mutahunter.core.pilot.aider.repomap import RepoMap
-from mutahunter.core.pilot.prompts.factory import PromptFactory
+from mutahunter.core.repomap import RepoMap
+from mutahunter.core.prompts.factory import PromptFactory
 
 
 class MutationStrategy:
@@ -42,15 +42,12 @@ def generate_mutations(
         ):
             start_byte = function_block.start_byte
             end_byte = function_block.end_byte
-            function_name = function_block.child_by_field_name("name").text.decode(
-                "utf8"
-            )
+
             mutant_generator = MutantGenerator(
                 config=hunter.config,
                 executed_lines=executed_lines,
                 cov_files=list(hunter.analyzer.file_lines_executed.keys()),
                 source_file_path=file_path,
-                function_name=function_name,
                 start_byte=start_byte,
                 end_byte=end_byte,
                 router=hunter.router,
@@ -96,7 +93,6 @@ def __init__(
         executed_lines,
         cov_files,
         source_file_path,  # file_path for the source code
-        function_name,
         start_byte,
         end_byte,
         router,
@@ -105,7 +101,6 @@ def __init__(
         self.executed_lines = executed_lines
         self.cov_files = cov_files
         self.source_file_path = source_file_path
-        self.function_name = function_name
         self.start_byte = start_byte
         self.end_byte = end_byte
         self.router = router
@@ -121,22 +116,36 @@ def get_function_block_source_code(self):
         return src_code[self.start_byte : self.end_byte].decode("utf-8")
 
     def generate_mutant(self, repo_map_result):
-        system_template = Template(self.prompt.system_prompt).render()
+        # add line number for each line of code
+        function_block_with_line_num = "\n".join(
+            [
+                f"{i + 1} {line}"
+                for i, line in enumerate(self.function_block_source_code.splitlines())
+            ]
+        )
+        system_template = Template(self.prompt.system_prompt).render(
+            language=self.language
+        )
         user_template = Template(self.prompt.user_prompt).render(
             language=self.language,
-            covered_lines=self.executed_lines,
             ast=repo_map_result,
-            function_name=self.function_name,
+            covered_lines=self.executed_lines,
             example_output=self.prompt.example_output,
-            function_block=self.function_block_source_code,
+            function_block=function_block_with_line_num,
+            maximum_num_of_mutants_per_function_block=3,
         )
         prompt = {
             "system": system_template,
             "user": user_template,
         }
+        print("system_template:", system_template)
+        print("user_template:", user_template)
+
+        exit()
         model_response, _, _ = self.router.generate_response(
             prompt=prompt, streaming=True
         )
+        # print("model_response", model_response)
         return model_response
 
     def generate(self):
@@ -150,6 +159,7 @@ def generate(self):
         ai_reply = self.generate_mutant(repo_map_result)
         mutation_info = self.extract_json_from_reply(ai_reply)
         changes = mutation_info["changes"]
+        print("changes:", len(changes))
         original_lines = self.function_block_source_code.splitlines(keepends=True)
         for change in changes:
             original_line = change["original_line"]