fix: bring a cached tier back as a tier, not as a bare string

Adding applied_effort to LLMResponse put it through the cache round
trip, where JSON stores a StrEnum as its plain value. Rehydrated raw, a
hit would hand downstream a str while the annotation says Effort, and
every `is Effort.LOW` in the library would quietly answer False on the
hit path only -- the same trap thinking_observation already has a
coercion for.

A value outside this version's vocabulary degrades to None rather than
failing the entry: projects sharing one Redis would otherwise keep
invalidating each other's writes over an attribution field, and None is
the honest reading of a tier this version cannot name.

tests/unit/test_cache.py

@@ -154,7 +154,6 @@ class TestKeyFormula:
             reasoning_effort=None,
         ) == ("pgw:cache:c54544e8672f4c91373b4a72716a88497445b440b89445aa5379b356b228f58b")
 
-
     def test_declared_tier_key_is_a_golden(self):
         """配了档位那一侧同样要有 golden: 字面量变了就是所有该档缓存冷启动。
 
@@ -402,6 +401,69 @@ class TestThinkingObservationRehydration:
         assert hit.thinking_observation is ThinkingObservation.UNKNOWN
 
 
+class TestAppliedEffortRehydration:
+    """issue #20: 实际档同样必须复活成枚举,理由与 `thinking_observation` 逐条相同。
+
+    JSON 里存的是 `StrEnum` 的字符串值;不转就复活成裸 str,而库内一路是
+    `is Effort.LOW` 的身份比较——命中路径上会静默判否,且下游拿到的类型与字段
+    注解分叉。缓存是档位的**第三条入口**(另两条是 `.env` 解析与 `chat()` 参数),
+    归一化不变式必须在这里也闭合。
+    """
+
+    async def test_hit_replays_enum_instance_not_bare_str(self):
+        backend = InMemoryCache()
+        mw = _mw(backend)
+        terminal = _Terminal(_resp(applied_effort=Effort.LOW))
+        await mw(ChatRequest(messages=_MSGS), terminal)
+        hit = await mw(ChatRequest(messages=_MSGS), terminal)
+        assert hit.cache_hit is True and terminal.calls == 1
+        assert isinstance(hit.applied_effort, Effort)
+        assert hit.applied_effort is Effort.LOW
+
+    async def test_unknown_tier_degrades_to_none_and_still_hits(self):
+        """域外档位降级为 None(=不知道这次跑在哪档),不作废内容完好的条目。
+
+        降级方向与 `thinking_observation` 同源: 共用一个 Redis 的项目里,先升级
+        的那个可能写入本版没有的档位名,未升级的项目若判成未命中,两个版本就会
+        互相打对方的缓存。归因字段不该有能力废掉一条内容完好的响应。
+        """
+        backend = InMemoryCache()
+        mw = _mw(backend)
+        key = build_cache_key("m", _MSGS, "proj", None)
+        poisoned = dataclasses.asdict(_resp(content="from-a-newer-version"))
+        poisoned["applied_effort"] = "ultra"
+        poisoned.pop("structured_data", None)
+        await backend.set(key, json.dumps(poisoned), 3600)
+        terminal = _Terminal(_resp())
+        messages: list[str] = []
+        sink_id = logger.add(messages.append, level="WARNING")
+        try:
+            resp = await mw(ChatRequest(messages=_MSGS), terminal)
+        finally:
+            logger.remove(sink_id)
+        assert terminal.calls == 0 and resp.cache_hit is True
+        assert resp.content == "from-a-newer-version"
+        assert resp.applied_effort is None
+        hits = [m for m in messages if "ultra" in m]
+        assert len(hits) == 1, f"域外档位必须单独告警一次,实得 {len(hits)} 条: {messages}"
+        assert "applied_effort" in hits[0]
+        assert [m for m in messages if "重建失败" in m] == []
+
+    async def test_legacy_entry_without_key_rehydrates_to_none(self):
+        """升级前写入的条目没有该键,必须照常复活并落到默认 None。"""
+        backend = InMemoryCache()
+        mw = _mw(backend)
+        key = build_cache_key("m", _MSGS, "proj", None)
+        legacy = dataclasses.asdict(_resp(content="legacy"))
+        legacy.pop("applied_effort")
+        legacy.pop("structured_data", None)
+        await backend.set(key, json.dumps(legacy), 3600)
+        terminal = _Terminal(_resp())
+        hit = await mw(ChatRequest(messages=_MSGS), terminal)
+        assert hit.content == "legacy" and terminal.calls == 0
+        assert hit.applied_effort is None
+
+
 class _BrokenBackend:
     async def get(self, key):
         raise ConnectionError("redis down")