victor-codegraph 0.10.1__tar.gz → 0.10.2__tar.gz

{victor_codegraph-0.10.1 → victor_codegraph-0.10.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: victor-codegraph
-Version: 0.10.1
+Version: 0.10.2
 Summary: Repository-to-Code-Semantic-Graph compiler with stable identity, bounded chunks, incremental deltas, and ProximaRecord projection.
 Author-email: Vijaykumar Singh <vijay@anvaiops.com>
 License: Apache-2.0
@@ -56,7 +56,11 @@ gaps:
 ## Install
 
 Published on PyPI as [`victor-codegraph`](https://pypi.org/project/victor-codegraph/).
-This source tree is version **0.10.1**; consumers should use a compatible `<1.0` pin.
+This source tree is version **0.10.2**; consumers should use a compatible `<1.0` pin.
+It repairs nested Python definition/import shadowing: proven local definitions
+retain their targets, while unmodeled conditional bindings stay unresolved.
+Rebuild derived graphs when adopting the new parser; unchanged source hashes do
+not invalidate old semantic results automatically. Publication is a separate gate.
 
 ```bash
 # from PyPI
@@ -128,7 +132,7 @@ records = to_proxima_records(repository, repo_graph_id="myrepo")
 
 ## Status
 
-`0.10.1` source version. Python (`ast`) is the full, offline frontend. JS/TS, Go, Rust,
+`0.10.2` source version. Python (`ast`) is the full, offline frontend. JS/TS, Go, Rust,
 Java, C, and C++ have conformance fixtures; other mapped tree-sitter languages report
 symbols-tier or fallback status rather than implying full fidelity.
 

{victor_codegraph-0.10.1 → victor_codegraph-0.10.2}/README.md

@@ -25,7 +25,11 @@ gaps:
 ## Install
 
 Published on PyPI as [`victor-codegraph`](https://pypi.org/project/victor-codegraph/).
-This source tree is version **0.10.1**; consumers should use a compatible `<1.0` pin.
+This source tree is version **0.10.2**; consumers should use a compatible `<1.0` pin.
+It repairs nested Python definition/import shadowing: proven local definitions
+retain their targets, while unmodeled conditional bindings stay unresolved.
+Rebuild derived graphs when adopting the new parser; unchanged source hashes do
+not invalidate old semantic results automatically. Publication is a separate gate.
 
 ```bash
 # from PyPI
@@ -97,7 +101,7 @@ records = to_proxima_records(repository, repo_graph_id="myrepo")
 
 ## Status
 
-`0.10.1` source version. Python (`ast`) is the full, offline frontend. JS/TS, Go, Rust,
+`0.10.2` source version. Python (`ast`) is the full, offline frontend. JS/TS, Go, Rust,
 Java, C, and C++ have conformance fixtures; other mapped tree-sitter languages report
 symbols-tier or fallback status rather than implying full fidelity.
 

{victor_codegraph-0.10.1 → victor_codegraph-0.10.2}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "victor-codegraph"
-version = "0.10.1"
+version = "0.10.2"
 description = "Repository-to-Code-Semantic-Graph compiler with stable identity, bounded chunks, incremental deltas, and ProximaRecord projection."
 readme = "README.md"
 requires-python = ">=3.12"

{victor_codegraph-0.10.1 → victor_codegraph-0.10.2}/tests/test_relations_v2.py

@@ -1,5 +1,7 @@
 from __future__ import annotations
 
+from pathlib import Path
+
 import pytest
 
 from victor_codegraph import CodeRelationType, parse, parse_repo, to_proxima_records
@@ -319,6 +321,40 @@ def test_python_enclosing_and_capture_bindings_block_import_guess(tmp_path, body
     assert calls and all(r.target_ref for r in calls)
 
 
+@pytest.mark.parametrize(
+    ("body", "target_scope"),
+    [
+        ("def caller():\n def target(): return 2\n return target()", ["caller"]),
+        ("async def caller():\n async def target(): return 2\n return await target()", ["caller"]),
+        ("def caller():\n class target: pass\n return target()", ["caller"]),
+        ("def outer():\n def target(): return 2\n def caller(): return target()", ["outer"]),
+        ("def caller(flag):\n if flag:\n  def target(): return 2\n return target()", None),
+        (
+            "def outer():\n def target(): return 2\n def caller(flag):\n  if flag:\n   def target(): return 3\n  return target()",
+            None,
+        ),
+        ("def caller(): return target()", []),
+    ],
+)
+def test_python_nearest_definition_precedes_import(
+    tmp_path: Path, body: str, target_scope: list[str] | None
+) -> None:
+    (tmp_path / "a.py").write_text("def target(): return 1\n")
+    (tmp_path / "b.py").write_text("from a import target\n" + body)
+    graph = parse_repo(tmp_path)
+    calls = [r for r in graph.relations if r.relation_type == CodeRelationType.CALLS]
+    assert len(calls) == 1
+    call = calls[0]
+    if target_scope is None:
+        assert call.target_ref is not None
+        assert call.confidence < 1.0
+    else:
+        target = next(s for s in graph.symbols if s.id == call.to_symbol_id)
+        assert call.target_ref is None
+        assert target.scope_chain == target_scope
+        assert target.location.file_path == ("b.py" if target_scope else "a.py")
+
+
 def test_python_reassigned_self_is_not_a_proven_receiver():
     parsed = parse(
         "class A:\n def target(self): pass\n def caller(self):\n  self = external\n  self.target()\n",

{victor_codegraph-0.10.1 → victor_codegraph-0.10.2}/victor_codegraph/__init__.py

@@ -54,7 +54,7 @@ from .repository_index import (
     relation_key,
 )
 
-__version__ = "0.10.1"
+__version__ = "0.10.2"
 
 __all__ = [
     "__version__",

{victor_codegraph-0.10.1 → victor_codegraph-0.10.2}/victor_codegraph/python_parser.py

@@ -8,6 +8,8 @@ signatures, docstrings, decorators, parameters, cyclomatic complexity, and CALLS
 from __future__ import annotations
 
 import ast
+from collections.abc import Iterator, Sequence
+from typing import NotRequired, TypedDict
 
 from .model import (
     CodeRelation,
@@ -47,13 +49,20 @@ def _cyclomatic(node: ast.AST) -> dict[str, int]:
     return {"cyclomatic": count, "lines": end - lineno + 1}
 
 
-def _params(args: ast.arguments) -> list[dict]:
-    out: list[dict] = []
+class _Parameter(TypedDict):
+    name: str
+    type: NotRequired[str]
+    is_variadic: NotRequired[bool]
+    is_kwonly: NotRequired[bool]
+
+
+def _params(args: ast.arguments) -> list[_Parameter]:
+    out: list[_Parameter] = []
     posonly = getattr(args, "posonlyargs", [])
     for a in [*posonly, *args.args]:
         if a.arg in ("self", "cls"):
             continue
-        p: dict = {"name": a.arg}
+        p: _Parameter = {"name": a.arg}
         if a.annotation is not None:
             p["type"] = ast.unparse(a.annotation)
         out.append(p)
@@ -109,7 +118,7 @@ def _callee_ref(call: ast.Call) -> SymbolReference | None:
     return None
 
 
-def _calls_owned_by(node: ast.AST):
+def _calls_owned_by(node: ast.AST) -> Iterator[ast.Call]:
     """Yield calls owned by ``node`` without stealing calls from nested definitions."""
 
     stack = list(ast.iter_child_nodes(node))
@@ -122,13 +131,15 @@ def _calls_owned_by(node: ast.AST):
         stack.extend(ast.iter_child_nodes(child))
 
 
-def _bound_names(nodes: list[ast.AST]) -> set[str]:
-    """Conservative lexical writes, including captures and deletion bindings."""
+def _lexical_bindings(nodes: Sequence[ast.AST]) -> tuple[set[str], set[str]]:
+    """Collect writes and definition bindings without entering nested namespaces."""
     names: set[str] = set()
+    definitions: set[str] = set()
     stack = list(nodes)
     while stack:
         node = stack.pop()
         if isinstance(node, (ast.FunctionDef, ast.AsyncFunctionDef, ast.ClassDef)):
+            definitions.add(node.name)
             continue
         if isinstance(node, ast.arg):
             names.add(node.arg)
@@ -141,7 +152,7 @@ def _bound_names(nodes: list[ast.AST]) -> set[str]:
         if isinstance(node, (ast.Import, ast.ImportFrom)):
             names.update(a.asname or a.name.split(".")[0] for a in node.names)
         stack.extend(ast.iter_child_nodes(node))
-    return names
+    return names, definitions
 
 
 class _Visitor:
@@ -152,6 +163,7 @@ class _Visitor:
         self.relations: list[CodeRelation] = []
         self.imports: list[str] = []
         self._enclosing_bindings: list[set[str]] = []
+        self._definition_scopes: list[dict[str, list[str]]] = [{}]
         self._import_names: set[str] = set()
         self._wildcard_import = False
         self._fqn_prefix = file_path.replace("/", ".").replace("\\", ".")
@@ -190,7 +202,7 @@ class _Visitor:
         symbol_type: CodeSymbolType,
         scope: list[str],
         signature: str | None = None,
-        params: list[dict] | None = None,
+        params: list[_Parameter] | None = None,
         return_type: str | None = None,
         modifiers: list[str] | None = None,
     ) -> CodeSymbol:
@@ -220,7 +232,7 @@ class _Visitor:
             signature=signature,
             modifiers=modifiers or [],
             scope_chain=list(scope),
-            parameters=params or [],
+            parameters=[dict(parameter) for parameter in params or []],
             return_type=return_type,
             complexity=_cyclomatic(node),
         )
@@ -254,10 +266,16 @@ class _Visitor:
             bound.add(node.args.vararg.arg)
         if node.args.kwarg:
             bound.add(node.args.kwarg.arg)
-        writes = _bound_names(node.body)
+        writes, definitions = _lexical_bindings(node.body)
+        inner = [*scope, name]
+        definition_scopes = {
+            **self._definition_scopes[-1],
+            **{definition: inner for definition in definitions},
+        }
         enclosing = set().union(*self._enclosing_bindings)
         sym.metadata["python_bound_names"] = sorted(bound | writes | enclosing)
         sym.metadata["python_rebound_names"] = sorted(writes | enclosing)
+        sym.metadata["python_definition_scopes"] = definition_scopes
         sym.metadata["python_import_names"] = sorted(self._import_names)
         sym.metadata["python_wildcard_import"] = self._wildcard_import
         sym.metadata["python_receiver"] = (
@@ -275,10 +293,10 @@ class _Visitor:
         # and otherwise keeps it as a bare name (so cross-file/external calls — e.g.
         # a CPG's blast radius — are not silently dropped). ``call_site`` records the
         # call line for consumers that need it.
-        for child in _calls_owned_by(node):
-            ref = _callee_ref(child)
+        for call in _calls_owned_by(node):
+            ref = _callee_ref(call)
             if ref:
-                line, col, end_line, end_col, offset, length = self._span(child)
+                line, col, end_line, end_col, offset, length = self._span(call)
                 self.relations.append(
                     CodeRelation(
                         from_symbol_id=sym.id,
@@ -297,8 +315,8 @@ class _Visitor:
                         ),
                     )
                 )
-        inner = [*scope, name]
         self._enclosing_bindings.append(bound | writes)
+        self._definition_scopes.append(definition_scopes)
         for child in node.body:
             nested: CodeSymbol | None = None
             if isinstance(child, (ast.FunctionDef, ast.AsyncFunctionDef)):
@@ -314,6 +332,7 @@ class _Visitor:
                     )
                 )
         self._enclosing_bindings.pop()
+        self._definition_scopes.pop()
         return sym
 
     def visit_class(self, node: ast.ClassDef, scope: list[str]) -> CodeSymbol:
@@ -322,6 +341,7 @@ class _Visitor:
         if bases:
             mods.append(f"extends({','.join(bases)})")
         cls = self._make_symbol(node, node.name, CodeSymbolType.CLASS, scope, modifiers=mods)
+        cls.metadata["python_definition_scopes"] = self._definition_scopes[-1]
         cls.metadata["python_rebound_names"] = sorted(set().union(*self._enclosing_bindings))
         self.symbols.append(cls)
         for base in bases:
@@ -356,9 +376,11 @@ class _Visitor:
         return cls
 
     def run(self, tree: ast.Module) -> None:
-        self._enclosing_bindings = [
-            _bound_names([n for n in tree.body if not isinstance(n, (ast.Import, ast.ImportFrom))])
-        ]
+        module_writes, _ = _lexical_bindings(
+            [n for n in tree.body if not isinstance(n, (ast.Import, ast.ImportFrom))]
+        )
+        self._enclosing_bindings = [module_writes]
+        self._definition_scopes = [{}]
         self._import_names = set()
         for declaration in tree.body:
             if isinstance(declaration, (ast.Import, ast.ImportFrom)):

{victor_codegraph-0.10.1 → victor_codegraph-0.10.2}/victor_codegraph/repository_index.py

@@ -7,6 +7,10 @@ import hashlib
 import os
 from dataclasses import asdict, dataclass, field, replace
 from pathlib import Path
+from typing import TYPE_CHECKING
+
+if TYPE_CHECKING:
+    from .rust_repository import RustBinding
 
 from .model import (
     CodeRelation,
@@ -67,7 +71,7 @@ def _resolve_across_files(
     symbols: list[CodeSymbol],
     relations: list[CodeRelation],
     files: dict[str, ParsedCode],
-    rust_bindings: dict[str, list] | None = None,
+    rust_bindings: dict[str, list[RustBinding]] | None = None,
     javascript: JavaScriptRepository | None = None,
 ) -> list[CodeRelation]:
     """Resolve only unambiguous repository targets; ambiguity remains explicit."""
@@ -147,11 +151,15 @@ def _resolve_across_files(
         if source.language == "python":
             text = ref.text or ref.name
             root, *tail = text.split(".")
-            if not source.metadata.get(
-                "python_wildcard_import"
-            ) and root not in source.metadata.get("python_bound_names", []):
-                for binding, targets in python_bindings.get(source.location.file_path, {}).items():
-                    prefix = binding.split(".")
+            if (
+                not source.metadata.get("python_wildcard_import")
+                and root not in source.metadata.get("python_bound_names", [])
+                and root not in source.metadata.get("python_definition_scopes", {})
+            ):
+                for import_name, targets in python_bindings.get(
+                    source.location.file_path, {}
+                ).items():
+                    prefix = import_name.split(".")
                     parts = text.split(".")
                     if parts[: len(prefix)] != prefix:
                         continue
@@ -198,7 +206,7 @@ def _python_bindings(
             if isinstance(node, ast.ImportFrom):
                 module = "." * node.level + (node.module or "")
                 name = alias.asname or alias.name
-                target = (alias.name,)
+                target: tuple[str, ...] = (alias.name,)
                 options = [
                     (module, target),
                     (module + ("." if node.module else "") + alias.name, ()),
@@ -347,7 +355,7 @@ def parse_repo(
 
     rust = RustRepository(root_path, resolution_files)
     javascript = JavaScriptRepository(resolution_files)
-    rust_bindings: dict[str, list] = {}
+    rust_bindings: dict[str, list[RustBinding]] = {}
     for relative, parsed in resolution_files.items():
         owner = file_symbols[relative]
         for symbol in parsed.symbols:

{victor_codegraph-0.10.1 → victor_codegraph-0.10.2}/victor_codegraph/resolution.py

@@ -72,6 +72,7 @@ def resolve_relations(
         if source is not None and source.language == "rust":
             candidates = _rust_candidates(source, ref, candidates, symbols)
         elif source is not None and source.language == "python":
+            definition_scope = source.metadata.get("python_definition_scopes", {}).get(ref.name)
             if source.metadata.get("python_wildcard_import"):
                 candidates = []
             elif ref.qualifier in {"self", "cls"}:
@@ -87,7 +88,10 @@ def resolve_relations(
             elif (
                 ref.qualifier
                 or ref.name in source.metadata.get("python_bound_names", [])
-                or ref.name in source.metadata.get("python_import_names", [])
+                or (
+                    ref.name in source.metadata.get("python_import_names", [])
+                    and definition_scope is None
+                )
             ):
                 candidates = []
             else:
@@ -104,6 +108,10 @@ def resolve_relations(
                     and [*source.scope_chain, source.simple_name][: len(c.scope_chain)]
                     == c.scope_chain
                 ]
+                # A lexical definition shadows imports and outer definitions even
+                # when its conditional body is not represented by this parser.
+                if definition_scope is not None:
+                    candidates = [c for c in candidates if c.scope_chain == definition_scope]
                 nearest = max((len(c.scope_chain) for c in candidates), default=-1)
                 candidates = [c for c in candidates if len(c.scope_chain) == nearest]
         elif source is not None and source.language in {"javascript", "typescript", "tsx"}:

{victor_codegraph-0.10.1 → victor_codegraph-0.10.2}/victor_codegraph.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: victor-codegraph
-Version: 0.10.1
+Version: 0.10.2
 Summary: Repository-to-Code-Semantic-Graph compiler with stable identity, bounded chunks, incremental deltas, and ProximaRecord projection.
 Author-email: Vijaykumar Singh <vijay@anvaiops.com>
 License: Apache-2.0
@@ -56,7 +56,11 @@ gaps:
 ## Install
 
 Published on PyPI as [`victor-codegraph`](https://pypi.org/project/victor-codegraph/).
-This source tree is version **0.10.1**; consumers should use a compatible `<1.0` pin.
+This source tree is version **0.10.2**; consumers should use a compatible `<1.0` pin.
+It repairs nested Python definition/import shadowing: proven local definitions
+retain their targets, while unmodeled conditional bindings stay unresolved.
+Rebuild derived graphs when adopting the new parser; unchanged source hashes do
+not invalidate old semantic results automatically. Publication is a separate gate.
 
 ```bash
 # from PyPI
@@ -128,7 +132,7 @@ records = to_proxima_records(repository, repo_graph_id="myrepo")
 
 ## Status
 
-`0.10.1` source version. Python (`ast`) is the full, offline frontend. JS/TS, Go, Rust,
+`0.10.2` source version. Python (`ast`) is the full, offline frontend. JS/TS, Go, Rust,
 Java, C, and C++ have conformance fixtures; other mapped tree-sitter languages report
 symbols-tier or fallback status rather than implying full fidelity.