feat(sdm): inject structural dependency mapping tags across codebase

Adds [C: caller] tags to functions/methods and [M: mutation] / [U: usage] tags to class variables based on cross-module call analysis.
This commit is contained in:
2026-05-13 22:35:41 -04:00
parent 5bb3a9026f
commit b5e512f483
110 changed files with 1673 additions and 1008 deletions
+37 -20
View File
@@ -47,13 +47,14 @@ _ast_cache: Dict[str, Tuple[float, tree_sitter.Tree]] = {}
class ASTParser:
"""
Parser for extracting AST-based views of source code.
Currently supports Python.
Parser for extracting AST-based views of source code.
Currently supports Python.
"""
#region: Core Operations
def __init__(self, language: str) -> None:
"""
[C: src/mcp_client.py:_DDGParser.__init__, src/mcp_client.py:_TextExtractor.__init__]
[C: src/mcp_client.py:_DDGParser.__init__, src/mcp_client.py:_TextExtractor.__init__]
"""
if language not in ("python", "cpp", "c"):
raise ValueError(f"Language '{language}' not supported yet.")
@@ -69,7 +70,8 @@ class ASTParser:
def parse(self, code: str) -> tree_sitter.Tree:
"""
Parse the given code and return the tree-sitter Tree.
Parse the given code and return the tree-sitter Tree.
[C: src/mcp_client.py:_search_file, src/mcp_client.py:derive_code_path, src/mcp_client.py:py_check_syntax, src/mcp_client.py:py_get_class_summary, src/mcp_client.py:py_get_definition, src/mcp_client.py:py_get_docstring, src/mcp_client.py:py_get_imports, src/mcp_client.py:py_get_signature, src/mcp_client.py:py_get_symbol_info, src/mcp_client.py:py_get_var_declaration, src/mcp_client.py:py_set_signature, src/mcp_client.py:py_set_var_declaration, src/mcp_client.py:py_update_definition, src/mcp_client.py:trace, src/outline_tool.py:CodeOutliner.outline, src/rag_engine.py:RAGEngine._chunk_code, src/summarize.py:_summarise_python, tests/test_ast_parser.py:test_ast_parser_parse, tests/test_tree_sitter_setup.py:test_tree_sitter_python_setup]
"""
return self.parser.parse(bytes(code, "utf8"))
@@ -185,7 +187,8 @@ class ASTParser:
def get_skeleton(self, code: str, path: Optional[str] = None) -> str:
"""
Returns a skeleton of a Python file (preserving docstrings, stripping function bodies).
Returns a skeleton of a Python file (preserving docstrings, stripping function bodies).
[C: src/mcp_client.py:py_get_skeleton, src/mcp_client.py:ts_c_get_skeleton, src/mcp_client.py:ts_cpp_get_skeleton, src/multi_agent_conductor.py:run_worker_lifecycle, tests/test_ast_parser.py:test_ast_parser_get_skeleton_c, tests/test_ast_parser.py:test_ast_parser_get_skeleton_cpp, tests/test_ast_parser.py:test_ast_parser_get_skeleton_python, tests/test_context_pruner.py:test_ast_caching, tests/test_context_pruner.py:test_performance_large_file]
"""
code_bytes = code.encode("utf8")
@@ -200,7 +203,7 @@ class ASTParser:
def walk(node: tree_sitter.Node) -> None:
"""
[C: src/mcp_client.py:_search_file, src/mcp_client.py:py_find_usages, src/mcp_client.py:py_get_hierarchy, src/mcp_client.py:trace, src/outline_tool.py:CodeOutliner.outline, src/outline_tool.py:CodeOutliner.walk, src/summarize.py:_summarise_python]
[C: src/mcp_client.py:_search_file, src/mcp_client.py:py_find_usages, src/mcp_client.py:py_get_hierarchy, src/mcp_client.py:trace, src/outline_tool.py:CodeOutliner.outline, src/outline_tool.py:CodeOutliner.walk, src/summarize.py:_summarise_python]
"""
if node.type == "function_definition":
body = node.child_by_field_name("body")
@@ -238,9 +241,10 @@ class ASTParser:
def get_curated_view(self, code: str, path: Optional[str] = None) -> str:
"""
Returns a curated skeleton of a Python file.
Preserves function bodies if they have @core_logic decorator or # [HOT] comment.
Otherwise strips bodies but preserves docstrings.
Returns a curated skeleton of a Python file.
Preserves function bodies if they have @core_logic decorator or # [HOT] comment.
Otherwise strips bodies but preserves docstrings.
[C: src/multi_agent_conductor.py:run_worker_lifecycle, tests/test_ast_parser.py:test_ast_parser_get_curated_view]
"""
code_bytes = code.encode("utf8")
@@ -279,7 +283,7 @@ class ASTParser:
def walk(node: tree_sitter.Node) -> None:
"""
[C: src/mcp_client.py:_search_file, src/mcp_client.py:py_find_usages, src/mcp_client.py:py_get_hierarchy, src/mcp_client.py:trace, src/outline_tool.py:CodeOutliner.outline, src/outline_tool.py:CodeOutliner.walk, src/summarize.py:_summarise_python]
[C: src/mcp_client.py:_search_file, src/mcp_client.py:py_find_usages, src/mcp_client.py:py_get_hierarchy, src/mcp_client.py:trace, src/outline_tool.py:CodeOutliner.outline, src/outline_tool.py:CodeOutliner.walk, src/summarize.py:_summarise_python]
"""
if node.type == "function_definition":
body = node.child_by_field_name("body")
@@ -317,8 +321,9 @@ class ASTParser:
def get_targeted_view(self, code: str, function_names: List[str], path: Optional[str] = None) -> str:
"""
Returns a targeted view of the code including only the specified functions
and their dependencies up to depth 2.
Returns a targeted view of the code including only the specified functions
and their dependencies up to depth 2.
[C: src/multi_agent_conductor.py:run_worker_lifecycle, tests/test_ast_parser.py:test_ast_parser_get_targeted_view, tests/test_context_pruner.py:test_class_targeted_extraction, tests/test_context_pruner.py:test_targeted_extraction]
"""
code_bytes = code.encode("utf8")
@@ -482,8 +487,9 @@ class ASTParser:
#region: Symbol Extraction
def get_definition(self, code: str, name: str, path: Optional[str] = None) -> str:
"""
Returns the full source code for a specific definition by name.
Supports 'ClassName::method' or 'method' for C++.
Returns the full source code for a specific definition by name.
Supports 'ClassName::method' or 'method' for C++.
[C: src/mcp_client.py:trace, src/mcp_client.py:ts_c_get_definition, src/mcp_client.py:ts_cpp_get_definition, tests/test_ast_parser.py:test_ast_parser_get_definition_c, tests/test_ast_parser.py:test_ast_parser_get_definition_cpp, tests/test_ast_parser.py:test_ast_parser_get_definition_cpp_template]
"""
code_bytes = code.encode("utf8")
@@ -492,6 +498,9 @@ class ASTParser:
parts = re.split(r'::|\.', name)
def walk(node: tree_sitter.Node, target_parts: List[str]) -> Optional[tree_sitter.Node]:
"""
[C: src/mcp_client.py:_search_file, src/mcp_client.py:py_find_usages, src/mcp_client.py:py_get_hierarchy, src/mcp_client.py:trace, src/outline_tool.py:CodeOutliner.outline, src/outline_tool.py:CodeOutliner.walk, src/summarize.py:_summarise_python]
"""
if not target_parts:
return None
target = target_parts[0]
@@ -578,8 +587,9 @@ class ASTParser:
def get_signature(self, code: str, name: str, path: Optional[str] = None) -> str:
"""
Returns only the signature part of a function or method.
For C/C++, this is the code from the start of the definition until the block start '{'.
Returns only the signature part of a function or method.
For C/C++, this is the code from the start of the definition until the block start '{'.
[C: src/mcp_client.py:ts_c_get_signature, src/mcp_client.py:ts_cpp_get_signature, tests/test_ast_parser.py:test_ast_parser_get_signature_c, tests/test_ast_parser.py:test_ast_parser_get_signature_cpp]
"""
code_bytes = code.encode("utf8")
@@ -588,6 +598,9 @@ class ASTParser:
parts = re.split(r'::|\.', name)
def walk(node: tree_sitter.Node, target_parts: List[str]) -> Optional[tree_sitter.Node]:
"""
[C: src/mcp_client.py:_search_file, src/mcp_client.py:py_find_usages, src/mcp_client.py:py_get_hierarchy, src/mcp_client.py:trace, src/outline_tool.py:CodeOutliner.outline, src/outline_tool.py:CodeOutliner.walk, src/summarize.py:_summarise_python]
"""
if not target_parts:
return None
target = target_parts[0]
@@ -687,7 +700,8 @@ class ASTParser:
def get_code_outline(self, code: str, path: Optional[str] = None) -> str:
"""
Returns a hierarchical outline of the code (classes, structs, functions, methods).
Returns a hierarchical outline of the code (classes, structs, functions, methods).
[C: src/mcp_client.py:ts_c_get_code_outline, src/mcp_client.py:ts_cpp_get_code_outline, tests/test_ast_parser.py:test_ast_parser_get_code_outline_c, tests/test_ast_parser.py:test_ast_parser_get_code_outline_cpp]
"""
code_bytes = code.encode("utf8")
@@ -696,7 +710,7 @@ class ASTParser:
def walk(node: tree_sitter.Node, indent: int = 0) -> None:
"""
[C: src/mcp_client.py:_search_file, src/mcp_client.py:py_find_usages, src/mcp_client.py:py_get_hierarchy, src/mcp_client.py:trace, src/outline_tool.py:CodeOutliner.outline, src/outline_tool.py:CodeOutliner.walk, src/summarize.py:_summarise_python]
[C: src/mcp_client.py:_search_file, src/mcp_client.py:py_find_usages, src/mcp_client.py:py_get_hierarchy, src/mcp_client.py:trace, src/outline_tool.py:CodeOutliner.outline, src/outline_tool.py:CodeOutliner.walk, src/summarize.py:_summarise_python]
"""
ntype = node.type
label = ""
@@ -728,7 +742,8 @@ class ASTParser:
def update_definition(self, code: str, name: str, new_content: str, path: Optional[str] = None) -> str:
"""
Surgically replace the definition of a class or function by name.
Surgically replace the definition of a class or function by name.
[C: src/mcp_client.py:ts_c_update_definition, src/mcp_client.py:ts_cpp_update_definition, tests/test_ast_parser.py:test_ast_parser_update_definition_cpp]
"""
code_bytes = code.encode("utf8")
@@ -737,6 +752,9 @@ class ASTParser:
parts = re.split(r'::|\.', name)
def walk(node: tree_sitter.Node, target_parts: List[str]) -> Optional[tree_sitter.Node]:
"""
[C: src/mcp_client.py:_search_file, src/mcp_client.py:py_find_usages, src/mcp_client.py:py_get_hierarchy, src/mcp_client.py:trace, src/outline_tool.py:CodeOutliner.outline, src/outline_tool.py:CodeOutliner.walk, src/summarize.py:_summarise_python]
"""
if not target_parts:
return None
target = target_parts[0]
@@ -830,4 +848,3 @@ def reset_client() -> None:
def get_file_id(path: Path) -> Optional[str]:
return None
#endregion: Module Level Utilities