feat(learning-harness): TypeScript and TSX rows parse under the semantic extra

Task 1.4. The optional extra gains the TypeScript grammar wheel, which ships two
grammars: a file with JSX needs the JSX-aware one and plain TypeScript needs the
other, so the parser picks by file suffix while the parsed file keeps the
language it was given. The walker already treated TypeScript as JavaScript, so
nothing else changes.

Eighteen agent-vfc rows and every TypeScript absence row were counted as
unsupported before this and could not be scored at all. They now parse on both
sides. The core install stays zero-dependency and the extra-free suite still
skips these tests.

Co-Authored-By: Claude Opus 5 (1M context) <[email protected]>
Claude-Session: https://claude.ai/code/session_01T7XD7x5KonMdmGRkp63EQG

src/openultrasast/semantic/cst.py

@@ -42,6 +42,7 @@ _KIND = {
 }
 _KIND["cpp"] = _KIND["c"]
 _KIND["typescript"] = _KIND["javascript"]
+_KIND["tsx"] = _KIND["javascript"]
 
 _CONST = frozenset(
     {
@@ -64,7 +65,7 @@ _SEQUENCE = frozenset({"list", "tuple", "array", "array_creation_expression", "i
 def parse_with_cst(path: str, text: str, language: str) -> FileIR | None:
     from .extra import grammar_for
 
-    grammar = grammar_for(language)
+    grammar = grammar_for(_grammar_language(language, path))
     if grammar is None:
         return None
     try:
@@ -77,6 +78,11 @@ def parse_with_cst(path: str, text: str, language: str) -> FileIR | None:
     return file_ir_from_tree(path=path, text=text, language=language, tree=tree)
 
 
+def _grammar_language(language: str, path: str) -> str:
+    """TypeScript ships two grammars; a `.tsx` file needs the JSX-aware one. The FileIR keeps the language it was given."""
+    return "tsx" if language == "typescript" and path.endswith(".tsx") else language
+
+
 def file_ir_from_tree(*, path: str, text: str, language: str, tree: Any) -> FileIR:
     del text
     root = tree.root_node

src/openultrasast/semantic/extra.py

@@ -7,12 +7,16 @@ import importlib.util
 import os
 from typing import Any
 
+# language -> (wheel module, the module attribute that builds the grammar). TypeScript ships two grammars;
+# `.tsx` needs the JSX-aware one and plain `.ts` needs the other, so the caller asks for the one it needs.
 _GRAMMAR_MODULES = {
-    "python": "tree_sitter_python",
-    "javascript": "tree_sitter_javascript",
-    "c": "tree_sitter_c",
-    "cpp": "tree_sitter_cpp",
-    "java": "tree_sitter_java",
+    "python": ("tree_sitter_python", "language"),
+    "javascript": ("tree_sitter_javascript", "language"),
+    "typescript": ("tree_sitter_typescript", "language_typescript"),
+    "tsx": ("tree_sitter_typescript", "language_tsx"),
+    "c": ("tree_sitter_c", "language"),
+    "cpp": ("tree_sitter_cpp", "language"),
+    "java": ("tree_sitter_java", "language"),
 }
 _PROBE_ENV = "OPENULTRASAST_TREE_SITTER_PROBE"
 _PROBE_OFF = frozenset({"0", "off", "false", "unavailable", "no"})
@@ -26,7 +30,7 @@ def has_semantic_extra() -> bool:
         return False
     if importlib.util.find_spec("tree_sitter") is None:
         return False
-    return any(importlib.util.find_spec(module) is not None for module in _GRAMMAR_MODULES.values())
+    return any(importlib.util.find_spec(module) is not None for module, _ in _GRAMMAR_MODULES.values())
 
 
 def grammar_for(language: str) -> Any | None:
@@ -34,15 +38,16 @@ def grammar_for(language: str) -> Any | None:
     flag = os.environ.get(_PROBE_ENV, "").strip().lower()
     if flag in _PROBE_OFF:
         return None
-    module_name = _GRAMMAR_MODULES.get(language)
-    if module_name is None or importlib.util.find_spec("tree_sitter") is None:
+    entry = _GRAMMAR_MODULES.get(language)
+    if entry is None or importlib.util.find_spec("tree_sitter") is None:
         return None
+    module_name, attribute = entry
     if importlib.util.find_spec(module_name) is None:
         return None
     try:
         from tree_sitter import Language
 
         module = importlib.import_module(module_name)
-        return Language(module.language())
+        return Language(getattr(module, attribute)())
     except Exception:
         return None