fix(python): a base imported from outside the project is not a project class of that name

CHANGELOG.md

@@ -25,9 +25,6 @@ and adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 - `codegraph serve --mcp --no-telemetry` turns telemetry off for one MCP server entry, so a shared MCP config can opt out without an environment variable; a background daemon that's already running for the project keeps its own setting until it exits. Thanks @danusha2345. (#1908)
 - `codegraph implementations <name>` lists the types that implement or extend a trait, interface or class, with each one's file and line, how it's tied to the type, and whether it's test code, a Rust mock in a `#[cfg(test)]` module included; `--depth` follows subclasses of subclasses. Thanks @danusha2345. (#2833)
 - Set `CODEGRAPH_SYNTH_MIN_INTERVAL_MS` to limit how often live syncs rebuild the callback and event links across the whole project, which on a large TypeScript or Vue repo otherwise happens on almost every edit; a rebuild that's put off runs when the interval is up even if no edit follows, and until then those links can be that far behind your code. A full `codegraph index` is never held. Thanks @danusha2345. (#2911)
-
-
-
 - New `codegraph cycles` command lists the groups of files that import each other in a circle, as text or `--json`, and exits 1 when it finds any, so it works as a pre-commit or CI check (#888). Thanks @jiangyq9 and @goutham80808.
 - `codegraph init --local-only` keeps `.codegraph/` out of git entirely, so nothing of CodeGraph's shows in `git status`, and it works on a project that's already set up, leaving a `.codegraph/.gitignore` you've edited or committed alone (#910). Thanks @jadchene, @jiangyq9, @Wood-Q and @walterf3.
 
@@ -47,6 +44,7 @@ and adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 - In Python, a call on a class or on a receiver named after it, like `Repo.save()` or `repo.save()` with `class Repo(Base[User])`, no longer links to a method of the base's type argument, like `User.save`. Before, every name in the base list counted as a supertype, so `User` was searched as if `Repo` inherited from it. The base itself, `Base`, is still searched. Re-index Python projects after upgrading. Thanks @JosefAschauer.
 - In Python, a class with a parameterized base, like `class Leaf(Base[str])`, `class Repo(models.Base[int])` or `class Both(Mixin, Base[str])`, is now linked to that base, as `class Leaf(Base)` already was, and a call through a module global holding such a class, like `current = Leaf()` then `current.run()`, reaches the method the base declares. Before, such a base was skipped, so the class had no `extends` edge and anything that follows the class hierarchy missed it. Re-index Python projects after upgrading. Thanks @JosefAschauer.
 - In Python, a class whose base list is wrapped over several lines, as black and ruff write a long one, now reaches the methods its bases declare, through a module global like `current = Wrapped()` then `current.run()` and through the class name like `Wrapped.run(x)`, as a one-line base list already did. Before, only the first line or three were read for this, so such a class seemed to have no bases. Re-index Python projects after upgrading. Thanks @JosefAschauer.
+- In Python, a base class your file imports from outside the project, like `class Color(Enum)` after `from enum import Enum` or `class Item(BaseModel)` after `from pydantic import BaseModel`, no longer links to a project class that only shares its name. Re-index Python projects after upgrading.
 - In Python, a call of your own class's method named like a dictionary, list or file method, such as `get`, `update`, `items`, `pop` or `close`, now links to that method when the function says what the variable holds: `reg = SystemPackRegistry()` then `reg.get(…)`, `registry = load_registry()` with `def load_registry() -> SystemPackRegistry`, or a parameter written `reg: SystemPackRegistry`. Before, these calls were dropped as built-in methods unless the variable was named after the class. A variable the function also sets to something else, like `{}` or what `json.load` returns, a class imported from another package, like `queue.Queue`, and a union type still link nothing. Re-index Python projects after upgrading. Thanks @inth3shadows for the report. (#2583)
 - In Python, Scala and Java, a standard-library method called on a value whose type CodeGraph can't see, like `options.setdefault(…)` on a dictionary, `m.getOrElse(…)` on an `Option` or `data.put(…)` on a map held in a `var`, no longer links to an unrelated project method that happens to share its name; the call still links when the variable is named after your class, like `registry.get(…)` for a `Registry`. Re-index Python, Scala and Java projects after upgrading. Thanks @danusha2345. (#1947)
 - In Python, a call on a module imported from outside your project, like `subprocess.run(…)` after `import subprocess`, no longer links to a project method that happens to share its name. Thanks @Egrn for the report. (#2599)

__tests__/python-outside-bases.test.ts

@@ -0,0 +1,189 @@
+/**
+ * A Python base the file imports from outside the project is that package's
+ * class, plain or parameterized: `class Color(Enum)` after `from enum import
+ * Enum` extends no project class that happens to be named `Enum`. Names the
+ * file binds to the project, or doesn't bind at all, keep linking.
+ */
+import { describe, it, expect, afterAll, beforeAll } from 'vitest';
+import * as fs from 'fs';
+import * as os from 'os';
+import * as path from 'path';
+import { CodeGraph } from '../src';
+
+const FILES: Record<string, string> = {
+  'app/__init__.py': '',
+  'app/schema.py': `class Enum:
+    pass
+
+
+class Sequence:
+    pass
+
+
+class Generic:
+    pass
+
+
+class Protocol:
+    pass
+
+
+class BaseModel:
+    pass
+
+
+class Thing:
+    pass
+`,
+  'app/outside.py': `from enum import Enum
+from typing import Generic, Protocol, Sequence, TypeVar
+
+from pydantic import BaseModel
+
+T = TypeVar("T")
+
+
+class Color(Enum):
+    pass
+
+
+class Plain(Sequence):
+    pass
+
+
+class Items(Sequence[int]):
+    pass
+
+
+class Box(Generic[T]):
+    pass
+
+
+class Greeter(Protocol[T]):
+    pass
+
+
+class Item(BaseModel):
+    pass
+
+
+class Row(BaseModel, Enum):
+    pass
+`,
+  'app/inside.py': `from app.schema import Sequence
+
+from .schema import Enum
+
+
+class Mine(Enum):
+    pass
+
+
+class Seq(Sequence[int]):
+    pass
+`,
+  'app/shadow.py': `from enum import Enum
+
+
+class Enum(Enum):
+    pass
+
+
+class Own(Enum):
+    pass
+`,
+  'app/fallback.py': `try:
+    from pydantic import BaseModel
+except ImportError:
+    from .schema import BaseModel
+
+
+class Either(BaseModel):
+    pass
+`,
+  'app/starred.py': `from .schema import *
+
+
+class Starred(Enum):
+    pass
+`,
+  'app/relative.py': `from .moved import Thing
+
+
+class Keep(Thing):
+    pass
+`,
+  'lib/support/helpers/base.py': `class Base:
+    pass
+`,
+  'tests/test_base.py': `from helpers.base import Base
+
+
+class TestBase(Base):
+    pass
+`,
+};
+
+let root = '';
+let cg: CodeGraph;
+
+beforeAll(async () => {
+  root = fs.mkdtempSync(path.join(os.tmpdir(), 'cg-py-outside-bases-'));
+  for (const [rel, content] of Object.entries(FILES)) {
+    fs.mkdirSync(path.dirname(path.join(root, rel)), { recursive: true });
+    fs.writeFileSync(path.join(root, rel), content);
+  }
+  cg = await CodeGraph.init(root, { index: true });
+});
+
+afterAll(() => {
+  cg?.close();
+  if (root) fs.rmSync(root, { recursive: true, force: true });
+});
+
+/** `file:class` of what the class `name` in `file` extends. */
+const bases = (file: string, name: string): string[] => {
+  const node = cg.getNodesInFile(file).find((n) => n.name === name && n.kind === 'class')!;
+  expect(node, name).toBeDefined();
+  return cg.getOutgoingEdges(node.id).filter((e) => e.kind === 'extends').map((e) => {
+    const target = cg.getNode(e.target)!;
+    return `${target.filePath}:${target.name}`;
+  });
+};
+
+describe('a Python base imported from outside the project', () => {
+  it('links no project class of that name, plain or parameterized', () => {
+    expect(bases('app/outside.py', 'Color')).toEqual([]);
+    expect(bases('app/outside.py', 'Plain')).toEqual([]);
+    expect(bases('app/outside.py', 'Items')).toEqual([]);
+    expect(bases('app/outside.py', 'Box')).toEqual([]);
+    expect(bases('app/outside.py', 'Greeter')).toEqual([]);
+    expect(bases('app/outside.py', 'Item')).toEqual([]);
+    expect(bases('app/outside.py', 'Row')).toEqual([]);
+  });
+
+  it('keeps a base the file imports from the project', () => {
+    expect(bases('app/inside.py', 'Mine')).toEqual(['app/schema.py:Enum']);
+    expect(bases('app/inside.py', 'Seq')).toEqual(['app/schema.py:Sequence']);
+  });
+
+  it('keeps a class the file declares itself under the imported name', () => {
+    expect(bases('app/shadow.py', 'Own')).toEqual(['app/shadow.py:Enum']);
+  });
+
+  it('keeps a base one of two imports of the name finds in the project', () => {
+    expect(bases('app/fallback.py', 'Either')).toEqual(['app/schema.py:BaseModel']);
+  });
+
+  it('keeps a base no named import binds', () => {
+    expect(bases('app/starred.py', 'Starred')).toEqual(['app/schema.py:Enum']);
+  });
+
+  it('keeps a base a relative import names, though that module is gone', () => {
+    expect(bases('app/relative.py', 'Keep')).toEqual(['app/schema.py:Thing']);
+  });
+
+  it('keeps a class in a file the import path names, though no search root finds it', () => {
+    expect(bases('tests/test_base.py', 'TestBase')).toEqual(['lib/support/helpers/base.py:Base']);
+  });
+});

src/resolution/import-resolver.ts

@@ -4312,7 +4312,7 @@ function resolveStaticMember(
  * instead of removing it, so locality has to be checked too.
  *
  * Answers only when it can be CERTAIN, because a false "yes" deletes a real
- * edge. Two languages qualify, each with an oracle that cannot be wrong:
+ * edge. Three languages qualify, each with an oracle of its own:
  *
  *  - **Rust** — the `use` path is rooted at a standard-library crate
  *    (`std`/`core`/`alloc`/`proc_macro`), which by definition ships outside
@@ -4325,21 +4325,27 @@ function resolveStaticMember(
  *    path aliases and monorepo workspace packages, unless the specifier still
  *    names a project file through the importing app's `baseUrl` or catch-all
  *    `paths` (`import Base from 'components/Base'`).
+ *  - **Python** — `resolveImportPath`, which searches for a module the way
+ *    Python does (see {@link isPythonNameFromOutside}).
  *
- * Everything else returns false and resolves exactly as before. JVM and Python
- * imports notably do NOT go through `resolveImportPath` (they have dedicated
- * FQN/module matchers), so there is no trustworthy oracle to consult here.
+ * Everything else returns false and resolves exactly as before. JVM imports
+ * notably do NOT go through `resolveImportPath` (they have dedicated FQN
+ * matchers), so there is no trustworthy oracle to consult here.
+ *
+ * `target` is what a strategy found, when the caller has it.
  */
 export function isBoundToOutOfRepoImport(
   ref: UnresolvedRef,
-  context: ResolutionContext
+  context: ResolutionContext,
+  target?: Node | null
 ): boolean {
   const name = ref.referenceName;
   if (name.includes('::') || name.includes('.')) return false; // qualified refs resolve by path
 
   // (A 2015-edition crate-relative path can shadow a stdlib root with a local
   // module of the same name: a `use core::…` with a `mod core;` is the crate's.)
   if (ref.language === 'rust') return isRustNameFromStd(ref, context);
+  if (ref.language === 'python') return isPythonNameFromOutside(ref, target, context);
 
   if (!ESM_IMPORT_LANGUAGES.has(ref.language)) return false;
   for (const imp of context.getImportMappings(ref.filePath, ref.language)) {
@@ -4353,6 +4359,30 @@ export function isBoundToOutOfRepoImport(
   return false;
 }
 
+/**
+ * Whether every import binding a Python name is of a module Python's search
+ * doesn't find in the project: `class Color(Enum)` after `from enum import
+ * Enum` is not the project's own `Enum`. That search can miss a project module
+ * only on a path the program sets up itself (`sys.path`), so a `target` in a
+ * file the import path names stays, as does one in the referring file, which
+ * may rebind the name (`class Enum(Enum)`). A relative import is the project's.
+ */
+function isPythonNameFromOutside(ref: UnresolvedRef, target: Node | null | undefined, context: ResolutionContext): boolean {
+  if (target?.filePath === ref.filePath) return false;
+  const bindings = context.getImportMappings(ref.filePath, 'python').filter((imp) => imp.localName === ref.referenceName);
+  return bindings.length > 0 && bindings.every((imp) =>
+    !imp.source.startsWith('.') &&
+    resolveImportPath(imp.source, ref.filePath, 'python', context) === null &&
+    !(target && isInPythonModulePath(target.filePath, imp.source)));
+}
+
+/** Whether `file` is the module `dotted` or inside it, under any root: `lib/x/helpers/base.py` for `helpers.base`. */
+function isInPythonModulePath(file: string, dotted: string): boolean {
+  const tail = `/${dotted.replace(/\./g, '/')}`;
+  const at = `/${file}`;
+  return at.includes(`${tail}/`) || at.endsWith(`${tail}.py`) || at.endsWith(`${tail}.pyi`);
+}
+
 /**
  * The tail a reference that failed to resolve is parked under when it goes
  * through an import binding the module's key finds and its own tail does not:

src/resolution/index.ts

@@ -4168,7 +4168,7 @@ export class ReferenceResolver {
       if (!type) return null;
       result = { ...result, targetNodeId: type.id };
     }
-    if (isBoundToOutOfRepoImport(ref, this.context)) return null;
+    if (isBoundToOutOfRepoImport(ref, this.context, target)) return null;
     // A Go type embedded through a package (`clientv3.KV`) is that package's.
     // When the package is none of the file's imports as indexed (clientv3
     // imported unaliased as `go.etcd.io/etcd/client/v3`), a type found by its