claude_refactor_v3: Add and passed test on splited gin-configs loading but without weigts

tests/conftest.py

@@ -0,0 +1,294 @@
+# """Shared pytest fixtures + reporter hooks for caption-test test suite.
+
+# Provides:
+#   - proj_dir, path2cfg: real repository paths for integration-style tests
+#     that load actual gin presets from in/config_files/.
+#   - clear_gin: autouse fixture that wipes gin global state before every test
+#     (gin keeps bindings in module-level singleton; tests must not leak).
+
+# Reporter hooks print "✅/❌ <docstring>" next to each test's PASSED/FAILED
+# line in -v mode.
+
+# Preset name lists live in a separate module (`tests/_presets.py`) so test
+# files can import them with a plain `import _presets` — no relative imports,
+# no need for tests/ to be a package.
+# """
+
+# from __future__ import annotations
+
+# from pathlib import Path
+
+# import gin
+# import pytest
+
+
+# DINOV3_PRESETS = (
+#     "gtauav_balanced",
+#     "gtauav_balanced_asym",
+#     "gtauav_baseline",
+#     "gtauav_baseline_asym",
+#     "gtauav_image_heavy",
+#     "gtauav_text_heavy",
+# )
+ 
+# STRIPNET_PRESETS = (
+#     "gtauav_balanced_stripnet",
+#     "gtauav_balanced_stripnet_unfrozen",
+#     "gtauav_baseline_stripnet",
+#     "gtauav_baseline_stripnet_unfrozen",
+# )
+ 
+# ALL_TRAINING_PRESETS = DINOV3_PRESETS + STRIPNET_PRESETS
+
+# # --- gin hygiene -----------------------------------------------------------
+
+
+# @pytest.fixture(autouse=True)
+# def clear_gin():
+#     """Wipe gin's global binding state before AND after each test.
+
+#     Gin keeps bindings in module-level singletons; without this fixture, a
+#     test that loads a config (or even just calls gin.parse_config_file in a
+#     helper) leaks bindings into the next test, leading to flaky failures
+#     like 'Unknown configurable' or wrong field values.
+#     """
+#     gin.clear_config()
+#     yield
+#     gin.clear_config()
+
+
+# # --- real-repo paths -------------------------------------------------------
+
+
+# @pytest.fixture
+# def proj_dir() -> Path:
+#     """Path to repository root (the directory that contains src/, tests/, in/)."""
+#     return Path(__file__).resolve().parent.parent
+
+
+# @pytest.fixture
+# def path2cfg(proj_dir: Path) -> str:
+#     """Trailing-slashed path to in/config_files/, matching `src/main.py`.
+
+#     Per REQUIREMENTS_GIN_STYLE.md §5, src/main.py builds this path as
+#     `f"{proj_dir}in/config_files/"`. Tests that exercise the real repo
+#     layout should use this fixture verbatim instead of constructing it
+#     independently.
+#     """
+#     return f"{proj_dir}/in/config_files/"
+
+
+# # --- reporter hooks --------------------------------------------------------
+
+
+# def _docstring_summary(item: pytest.Item) -> str | None:
+#     """Return the first non-empty line of a test's docstring, or None."""
+#     func = getattr(item, "function", None) or getattr(item, "obj", None)
+#     if func is None or not getattr(func, "__doc__", None):
+#         return None
+#     for line in func.__doc__.strip().splitlines():
+#         stripped = line.strip()
+#         if stripped:
+#             return stripped
+#     return None
+
+
+# # Cache nodeid → docstring summary, populated at collection time so the
+# # logreport hook can look them up without re-introspecting the test function.
+# _LAST_SEEN_SUMMARY: dict[str, str] = {}
+
+
+# def pytest_collection_modifyitems(
+#     config: pytest.Config,
+#     items: list[pytest.Item],
+# ) -> None:
+#     """Cache each item's docstring summary for later use by the status hook."""
+#     for item in items:
+#         summary = _docstring_summary(item)
+#         if summary:
+#             _LAST_SEEN_SUMMARY[item.nodeid] = summary
+
+
+# def pytest_runtest_logreport(report: pytest.TestReport) -> None:
+#     """Print '✅/❌/⏭️ <docstring>' after each test's `call` phase finishes.
+
+#     Pytest emits 3 reports per test (setup → call → teardown). We hook the
+#     `call` phase — the one where pass/fail is actually decided — and write
+#     the icon + docstring summary to stdout, where it appears next to
+#     pytest's own PASSED/FAILED line.
+#     """
+#     if report.when != "call":
+#         return
+
+#     summary = _LAST_SEEN_SUMMARY.get(report.nodeid, "(no docstring)")
+#     if report.passed:
+#         icon = "✅"
+#     elif report.failed:
+#         icon = "❌"
+#     else:
+#         icon = "⏭️"
+#     print(f"  {icon}  {summary}")
+
+
+
+
+
+
+
+"""Shared pytest fixtures + reporter hooks for caption-test test suite.
+
+Provides:
+  - proj_dir, path2cfg: real repository paths for integration-style tests
+    that load actual gin presets from in/config_files/.
+  - clear_gin: autouse fixture that wipes gin global state before every test
+    (gin keeps bindings in module-level singleton; tests must not leak).
+
+Reporter hooks print "✅/❌ <docstring>" next to each test's PASSED/FAILED
+line in -v mode.
+
+Preset name lists live in a separate module (`tests/_presets.py`) so test
+files can import them with a plain `import _presets` — no relative imports,
+no need for tests/ to be a package.
+"""
+
+from __future__ import annotations
+
+from pathlib import Path
+
+import gin
+import pytest
+
+
+DINOV3_PRESETS = (
+    "gtauav_balanced",
+    "gtauav_balanced_asym",
+    "gtauav_baseline",
+    "gtauav_baseline_asym",
+    "gtauav_image_heavy",
+    "gtauav_text_heavy",
+)
+ 
+STRIPNET_PRESETS = (
+    "gtauav_balanced_stripnet",
+    "gtauav_balanced_stripnet_unfrozen",
+    "gtauav_baseline_stripnet",
+    "gtauav_baseline_stripnet_unfrozen",
+)
+ 
+ALL_TRAINING_PRESETS = DINOV3_PRESETS + STRIPNET_PRESETS
+
+# --- gin hygiene -----------------------------------------------------------
+
+
+@pytest.fixture(autouse=True)
+def clear_gin():
+    """Wipe gin's global binding state before AND after each test.
+
+    Gin keeps bindings in module-level singletons; without this fixture, a
+    test that loads a config (or even just calls gin.parse_config_file in a
+    helper) leaks bindings into the next test, leading to flaky failures
+    like 'Unknown configurable' or wrong field values.
+    """
+    gin.clear_config()
+    yield
+    gin.clear_config()
+
+
+# --- real-repo paths -------------------------------------------------------
+
+
+@pytest.fixture
+def proj_dir() -> Path:
+    """Path to repository root (the directory that contains src/, tests/, in/)."""
+    return Path(__file__).resolve().parent.parent
+
+
+@pytest.fixture
+def path2cfg(proj_dir: Path) -> str:
+    """Trailing-slashed path to in/config_files/, matching `src/main.py`.
+
+    Per REQUIREMENTS_GIN_STYLE.md §5, src/main.py builds this path as
+    `f"{proj_dir}in/config_files/"`. Tests that exercise the real repo
+    layout should use this fixture verbatim instead of constructing it
+    independently.
+    """
+    return f"{proj_dir}/in/config_files/"
+
+
+# --- reporter hooks --------------------------------------------------------
+
+
+def _docstring_summary(item: pytest.Item) -> str | None:
+    """Return the first non-empty line of a test's docstring, or None."""
+    func = getattr(item, "function", None) or getattr(item, "obj", None)
+    if func is None or not getattr(func, "__doc__", None):
+        return None
+    for line in func.__doc__.strip().splitlines():
+        stripped = line.strip()
+        if stripped:
+            return stripped
+    return None
+
+
+# Cache nodeid → docstring summary, populated at collection time so the
+# logreport hook can look them up without re-introspecting the test function.
+_LAST_SEEN_SUMMARY: dict[str, str] = {}
+
+
+def pytest_collection_modifyitems(
+    config: pytest.Config,
+    items: list[pytest.Item],
+) -> None:
+    """Cache each item's docstring summary for later use by the status hook."""
+    for item in items:
+        summary = _docstring_summary(item)
+        if summary:
+            _LAST_SEEN_SUMMARY[item.nodeid] = summary
+
+
+def pytest_runtest_logreport(report: pytest.TestReport) -> None:
+    """Print test results with parametrized tests grouped under one header.
+
+    Non-parametrized test:
+        ✅  <docstring summary>
+
+    Parametrized test (first occurrence of the group):
+        <docstring summary>
+          ✅  <param>
+
+    Parametrized test (subsequent occurrences):
+          ✅  <param>
+
+    Pytest emits 3 reports per test (setup → call → teardown). We hook the
+    `call` phase — the one where pass/fail is actually decided.
+    """
+    if report.when != "call":
+        return
+
+    summary = _LAST_SEEN_SUMMARY.get(report.nodeid, "(no docstring)")
+    if report.passed:
+        icon = "✅"
+    elif report.failed:
+        icon = "❌"
+    else:
+        icon = "⏭️"
+
+    # Detect parametrization: pytest encodes params as `nodeid[param1-param2-...]`.
+    if "[" in report.nodeid and report.nodeid.endswith("]"):
+        base_id, _, param_part = report.nodeid.partition("[")
+        param_label = param_part[:-1] or "empty" # strip trailing ']'
+
+        # Print docstring header only on first encounter of this group.
+        # Leading "\n" separates the header from pytest's progress dot.
+        if base_id not in _PRINTED_GROUP_HEADERS:
+            print(f"\n{summary}")
+            _PRINTED_GROUP_HEADERS.add(base_id)
+        print(f"  {icon}  {param_label}")
+    else:
+        print(f"  {icon}  {summary}")
+
+
+# Tracks which parametrized test groups have already had their docstring
+# header printed. Reset implicitly at the start of each pytest run because
+# Python re-imports conftest.py.
+_PRINTED_GROUP_HEADERS: set[str] = set()