diff --git a/src/polygateway/middleware/cache.py b/src/polygateway/middleware/cache.py
index 88a63a7..52f0fa1 100644
--- a/src/polygateway/middleware/cache.py
+++ b/src/polygateway/middleware/cache.py
@@ -17,7 +17,7 @@ from typing import TYPE_CHECKING, Any
 
 from loguru import logger
 
-from polygateway.types import ChatRequest, LLMResponse
+from polygateway.types import ChatRequest, LLMResponse, ThinkingObservation
 
 if TYPE_CHECKING:
     from collections.abc import Mapping
@@ -132,6 +132,12 @@ class CacheMW:
             data = json.loads(raw)
             fields = {k: v for k, v in data.items() if k in _RESPONSE_FIELDS}
             structured_data = self._rebuild_structured(fields.get("content", ""), request)
+            # JSON 里存的是 StrEnum 的字符串值,不转就复活成裸 str,与字段注解分叉
+            # (下游 `is ThinkingObservation.OBSERVED` 会在命中路径上静默为 False);
+            # 键缺失即升级前写入的旧条目,交给 dataclass 默认值。域外值抛
+            # ValueError,由下方 except 吞成"按未命中回源"——降级方向正确。
+            if "thinking_observation" in fields:
+                fields["thinking_observation"] = ThinkingObservation(fields["thinking_observation"])
             fields.update(
                 cache_hit=True,
                 latency_ms=0,
diff --git a/tests/unit/test_cache.py b/tests/unit/test_cache.py
index 1b28405..156e6a1 100644
--- a/tests/unit/test_cache.py
+++ b/tests/unit/test_cache.py
@@ -10,7 +10,7 @@ from polygateway.backends.memory.cache import InMemoryCache
 from polygateway.errors import ResultInvalidError, TransientError
 from polygateway.middleware.cache import CacheMW, build_cache_key, digest_messages
 from polygateway.middleware.telemetry import TelemetryEmitter
-from polygateway.types import ChatRequest, LLMResponse, SourceConfig
+from polygateway.types import ChatRequest, LLMResponse, SourceConfig, ThinkingObservation
 
 _MSGS = [{"role": "user", "content": "hi"}]
 
@@ -249,6 +249,52 @@ class TestObservabilityFieldsOnHit:
         assert hit.cached_prompt_tokens is None and hit.model_reported is None
 
 
+class TestThinkingObservationRehydration:
+    """issue #16/#17: 命中回放必须复活成枚举实例,而不是 JSON 里的裸 str。
+
+    裸 str 与字段注解分叉,下游拿 `resp.thinking_observation is
+    ThinkingObservation.OBSERVED` 判等会在缓存命中路径上静默为 False。
+    """
+
+    async def test_hit_replays_enum_instance_not_bare_str(self):
+        backend = InMemoryCache()
+        mw = _mw(backend)
+        terminal = _Terminal(_resp(thinking_observation=ThinkingObservation.OBSERVED))
+        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.thinking_observation, ThinkingObservation)
+        assert hit.thinking_observation is ThinkingObservation.OBSERVED
+
+    async def test_illegal_value_falls_back_to_source(self):
+        """污染值(旧版本写入或人为篡改)按未命中回源,不得复活出域外取值。"""
+        backend = InMemoryCache()
+        mw = _mw(backend)
+        key = build_cache_key("m", _MSGS, "proj", None)
+        poisoned = dataclasses.asdict(_resp(content="poisoned"))
+        poisoned["thinking_observation"] = "bogus"
+        poisoned.pop("structured_data", None)
+        await backend.set(key, json.dumps(poisoned), 3600)
+        terminal = _Terminal(_resp())
+        resp = await mw(ChatRequest(messages=_MSGS), terminal)
+        assert terminal.calls == 1 and resp.cache_hit is False
+        assert resp.content == "cached"  # 回源结果,不是被污染的那条
+
+    async def test_legacy_entry_without_key_rehydrates_to_default(self):
+        """升级前写入的条目没有该键,必须照常复活并落到默认 UNKNOWN。"""
+        backend = InMemoryCache()
+        mw = _mw(backend)
+        key = build_cache_key("m", _MSGS, "proj", None)
+        legacy = dataclasses.asdict(_resp(content="legacy"))
+        legacy.pop("thinking_observation")
+        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.thinking_observation is ThinkingObservation.UNKNOWN
+
+
 class _BrokenBackend:
     async def get(self, key):
         raise ConnectionError("redis down")