feat: Add file-types command

README.md

@@ -136,6 +136,8 @@ generated/     # exclude generated dir
 !*.cob         # include COBOL files
 ```
 
+Run `semble file-types` to see which extensions are indexed per content type. Extensions not listed (including data files such as `.json` and `.csv`) are not indexed by default and can be force-included with a `!` pattern as above.
+
 Semble also always skips a set of well-known non-source directories regardless of ignore files (e.g. `node_modules/`, `.venv/`, `dist/`, `build/`, `__pycache__/`, and similar).
 
 </details>

src/semble/cli.py

@@ -18,6 +18,7 @@
 
 from semble.cache import cache_key, resolve_cache_folder, save_index_to_cache
 from semble.index import SembleIndex
+from semble.index.files import get_extensions
 from semble.index.types import PersistencePath
 from semble.installer.agents import AGENTS, IntegrationType
 from semble.stats import format_savings_report
@@ -26,7 +27,19 @@
 from semble.version import __version__
 
 _CLI_DISPATCH_ARGS = frozenset(
-    {"search", "find-related", "install", "uninstall", "savings", "-h", "--help", "clear", "--version", "-V"}
+    {
+        "search",
+        "find-related",
+        "file-types",
+        "install",
+        "uninstall",
+        "savings",
+        "-h",
+        "--help",
+        "clear",
+        "--version",
+        "-V",
+    }
 )
 _CLEAR_CHOICE = Literal["all", "index", "savings", "orphans"]
 
@@ -292,6 +305,16 @@ def _cli_main() -> None:
     related_p.add_argument("line", type=int, help="Line number (1-indexed).")
     _add_query_args(related_p)
 
+    file_types_p = sub.add_parser("file-types", help="List the file extensions indexed per content type.")
+    file_types_p.add_argument(
+        "--content",
+        nargs="+",
+        default=["all"],
+        choices=[ct.value for ct in ContentType] + ["all"],
+        metavar="TYPE",
+        help="Content types to list (space-separated). Choices: code, docs, config, all. Default: all.",
+    )
+
     sub.add_parser("savings", help="Show token savings and usage stats.")
 
     install_p = sub.add_parser("install", help="Configure semble across coding agents.")
@@ -332,6 +355,8 @@ def _cli_main() -> None:
         run(args.command, agent_ids=args.agent, integration_ids=integration_ids, yes=args.yes)
     elif args.command == "clear":
         _run_clear(args.type)
+    elif args.command == "file-types":
+        print(json.dumps({ct.value: get_extensions([ct]) for ct in _resolve_content(args.content, False)}))
     elif args.command == "search":
         _run_search(
             args.path,

src/semble/version.py

@@ -1,2 +1,2 @@
-__version_triple__ = (0, 6, 2)
+__version_triple__ = (0, 7, 0)
 __version__ = ".".join(map(str, __version_triple__))

tests/test_cli.py

@@ -478,3 +478,22 @@ def test_cli_clear_command(
         assert not (tmp_path / sha).exists()
     if setup_savings:
         assert not savings_file.exists()
+
+
+@pytest.mark.parametrize(
+    ("content", "expected"),
+    [
+        ([], {"code": ".py", "docs": ".md", "config": ".toml"}),
+        (["--content", "docs"], {"docs": ".md"}),
+    ],
+)
+def test_cli_file_types(
+    content: list[str], expected: dict[str, str], monkeypatch: pytest.MonkeyPatch, capsys: pytest.CaptureFixture[str]
+) -> None:
+    """`semble file-types` prints the indexed extensions per requested content type."""
+    monkeypatch.setattr(sys, "argv", ["semble", "file-types", *content])
+    main()
+    out = json.loads(capsys.readouterr().out)
+    assert list(out) == list(expected)
+    assert all(extension in out[content_type] for content_type, extension in expected.items())
+    assert all(".json" not in extensions for extensions in out.values())