[Migrate] Move sampling parameter overrides from legacy dispatches to TTS adapters (#5272)

Signed-off-by: boatman <109857087+sphinxkkkbc@users.noreply.github.com>

tools/pre_commit/check_tts_adapter.py

@@ -6,10 +6,8 @@ Per-model behaviour is being moved out of ``serving_speech.py`` and into
 nothing stopped a new model from adding one more ``self._tts_model_type == ...``
 branch faster than the migration removed them.
 
-This gate makes the two debt counters monotonically non-increasing:
-
-1. ``self._tts_model_type`` comparisons in ``serving_speech.py``
-2. entries in ``tts_adapters.LEGACY_TTS_DETECTORS`` (models with no adapter)
+This gate makes the number of ``self._tts_model_type`` comparisons in
+``serving_speech.py`` monotonically non-increasing.
 
 Lowering a budget after removing branches is expected and encouraged — the check
 insists on it, so the recorded numbers cannot silently drift upward. Raising one
@@ -28,11 +26,9 @@ from pathlib import Path
 
 REPO_ROOT = Path(__file__).resolve().parents[2]
 SERVING_SPEECH = Path("vllm_omni/entrypoints/openai/serving_speech.py")
-ADAPTERS_INIT = Path("vllm_omni/entrypoints/openai/tts_adapters/__init__.py")
 
 # Budgets. These may only go DOWN. See the module docstring.
-MAX_MODEL_TYPE_BRANCHES = 27
-MAX_LEGACY_DETECTORS = 0
+MAX_MODEL_TYPE_BRANCHES = 20
 
 _GUIDANCE = """
 Move the per-model behaviour into its adapter under
@@ -109,20 +105,6 @@ def _model_type_branches(tree: ast.AST) -> list[tuple[int, str]]:
     return found
 
 
-def _legacy_detectors(tree: ast.AST) -> list[tuple[int, str]]:
-    """Every ``LegacyDetector(...)`` construction."""
-    found: list[tuple[int, str]] = []
-    for node in ast.walk(tree):
-        if isinstance(node, ast.Call) and isinstance(node.func, ast.Name) and node.func.id == "LegacyDetector":
-            name = "?"
-            for kw in node.keywords:
-                if kw.arg == "name" and isinstance(kw.value, ast.Constant):
-                    name = str(kw.value.value)
-            found.append((node.lineno, name))
-    found.sort()
-    return found
-
-
 def _check(
     label: str,
     path: Path,
@@ -151,21 +133,18 @@ def _check(
 
 def main(argv: list[str] | None = None) -> int:
     parser = argparse.ArgumentParser(description=__doc__)
-    # pre-commit passes the staged filenames; we always audit the same two files,
+    # pre-commit passes the staged filenames; we always audit the same file,
     # so they are accepted and ignored.
     parser.add_argument("filenames", nargs="*")
     parser.parse_args(argv)
 
     serving_path = REPO_ROOT / SERVING_SPEECH
-    adapters_path = REPO_ROOT / ADAPTERS_INIT
-    for path in (serving_path, adapters_path):
-        if not path.is_file():
-            print(f"check_tts_adapter: expected file not found: {path}", file=sys.stderr)
-            return 1
+    if not serving_path.is_file():
+        print(f"check_tts_adapter: expected file not found: {serving_path}", file=sys.stderr)
+        return 1
 
     notices: list[str] = []
     branches = _model_type_branches(ast.parse(serving_path.read_text()))
-    detectors = _legacy_detectors(ast.parse(adapters_path.read_text()))
 
     errors = _check(
         "`_tts_model_type` comparisons",
@@ -176,15 +155,6 @@ def main(argv: list[str] | None = None) -> int:
         "MAX_MODEL_TYPE_BRANCHES",
         notices,
     )
-    errors += _check(
-        "unmigrated model types in LEGACY_TTS_DETECTORS",
-        ADAPTERS_INIT,
-        len(detectors),
-        MAX_LEGACY_DETECTORS,
-        [f"line {lineno}: {name}" for lineno, name in detectors],
-        "MAX_LEGACY_DETECTORS",
-        notices,
-    )
 
     for notice in notices:
         print(f"check_tts_adapter: {notice}", file=sys.stderr)