chore: snapshot in-progress question-gen work before preflight fixes

tests/unit/test_core_protocols.py

@@ -1,11 +1,10 @@
 """core/protocols.py 单元测试 — 验证 Protocol 可 runtime_checkable。"""
+
 from __future__ import annotations
 
 from pathlib import Path
 from typing import Any
 
-import pytest
-
 from core.protocols import LLMProvider, TelemetryRecorder, VLMProvider
 from core.types import LLMResponse
 
@@ -19,9 +18,17 @@ class _FakeLLM:
         parent_call_id: str | None = None,
     ) -> LLMResponse:
         return LLMResponse(
-            content="ok", thinking="", model="m", provider="p",
-            prompt_tokens=1, completion_tokens=1, latency_ms=1,
-            ttft_ms=None, max_inter_token_ms=None, cache_hit=False, call_id="c",
+            content="ok",
+            thinking="",
+            model="m",
+            provider="p",
+            prompt_tokens=1,
+            completion_tokens=1,
+            latency_ms=1,
+            ttft_ms=None,
+            max_inter_token_ms=None,
+            cache_hit=False,
+            call_id="c",
         )
 
 
@@ -35,19 +42,39 @@ class _FakeVLM:
         parent_call_id: str | None = None,
     ) -> LLMResponse:
         return LLMResponse(
-            content="ok", thinking="", model="m", provider="p",
-            prompt_tokens=1, completion_tokens=1, latency_ms=1,
-            ttft_ms=None, max_inter_token_ms=None, cache_hit=False, call_id="c",
+            content="ok",
+            thinking="",
+            model="m",
+            provider="p",
+            prompt_tokens=1,
+            completion_tokens=1,
+            latency_ms=1,
+            ttft_ms=None,
+            max_inter_token_ms=None,
+            cache_hit=False,
+            call_id="c",
         )
 
 
 class _FakeTelemetry:
     async def record_llm_call(
-        self, *, call_id: str, parent_call_id: str | None, session_id: str | None,
-        model_name: str, provider: str, messages: str, response: str, thinking: str,
-        prompt_tokens: int, completion_tokens: int, latency_ms: int,
-        ttft_ms: float | None, max_inter_token_ms: float | None,
-        cache_hit: bool, error: str | None,
+        self,
+        *,
+        call_id: str,
+        parent_call_id: str | None,
+        session_id: str | None,
+        model_name: str,
+        provider: str,
+        messages: str,
+        response: str,
+        thinking: str,
+        prompt_tokens: int,
+        completion_tokens: int,
+        latency_ms: int,
+        ttft_ms: float | None,
+        max_inter_token_ms: float | None,
+        cache_hit: bool,
+        error: str | None,
     ) -> None:
         pass
 
@@ -55,12 +82,15 @@ class _FakeTelemetry:
 def test_fake_llm_satisfies_protocol() -> None:
     assert isinstance(_FakeLLM(), LLMProvider)
 
+
 def test_fake_vlm_satisfies_protocol() -> None:
     assert isinstance(_FakeVLM(), VLMProvider)
 
+
 def test_fake_telemetry_satisfies_protocol() -> None:
     assert isinstance(_FakeTelemetry(), TelemetryRecorder)
 
+
 def test_plain_object_does_not_satisfy() -> None:
     assert not isinstance(object(), LLMProvider)
     assert not isinstance(object(), VLMProvider)
@@ -80,8 +110,11 @@ class TestPoolStrategyProtocol:
         class FakeStrategy:
             def build(self, questions, correctness, config):
                 return Pools(
-                    diagnosis=[], validation=[], test=[],
-                    baseline_run_id="", baseline_val_accuracy=0.0,
+                    diagnosis=[],
+                    validation=[],
+                    test=[],
+                    baseline_run_id="",
+                    baseline_val_accuracy=0.0,
                 )
 
             def build_incremental(self, new_task_types, questions, correctness, config):