test: deduplicate suites and prune low-value cases

- extract shared helpers for dataset writers, scheduler construction, thread interleaving, hf roundtrips, and moe configs
- remove about 20 cases whose only assertions were format checks, restated declarations, fake-taxonomy duplicates, or test-local scaffolding
- strengthen weak cases into exact reference comparisons, positional mask checks, and deterministic outcomes
- replace two schedule factory smoke tests with cosine/sgdr formula assertions
- delete root-level CLI tests whose merge-priority facts are covered by tests/config/test_cli.py
- suite shrinks from 857 to 826 items; ruff format, import order, and pytest all green

tests/inference/test_protocol.py

@@ -71,31 +71,6 @@ def test_check_empty_sequences():
     assert sc.check("hello") is None
 
 
-def test_gen_context_defaults():
-    ctx = GenContext(resp_id="a", created=1, model="m", prompt_tokens=10)
-    assert ctx.completion_tokens == 0
-
-
-def test_gen_context_fields_mutable():
-    ctx = GenContext(resp_id="a", created=1, model="m", prompt_tokens=10)
-    ctx.completion_tokens = 42
-    assert ctx.completion_tokens == 42
-
-
-def test_stop_info_defaults():
-    s = StopInfo()
-    assert s.matched is None
-    assert s.body == ""
-    assert s.yielded == ""
-
-
-def test_stop_info_with_values():
-    s = StopInfo(matched="stop", body="hello stop", yielded="hello ")
-    assert s.matched == "stop"
-    assert s.body == "hello stop"
-    assert s.yielded == "hello "
-
-
 def test_openai_prepare_returns_prompt_ctx_stops():
     builder = _make_openai_builder()
     req = MagicMock()