feat: carry the new observability fields through retry and cache

tests/unit/test_cache.py

@@ -150,6 +150,49 @@ class TestCacheFlow:
         assert terminal.calls == 2
 
 
+class TestObservabilityFieldsOnHit:
+    """issue #3 决策 B1: 命中行原样回放,与 model/prompt_tokens 同一口径。"""
+
+    async def test_fields_replayed_on_hit(self):
+        backend = InMemoryCache()
+        mw = _mw(backend)
+        terminal = _Terminal(
+            _resp(cached_prompt_tokens=64, model_reported="MiniMax-Text-01-250321")
+        )
+        await mw(ChatRequest(messages=_MSGS), terminal)
+        hit = await mw(ChatRequest(messages=_MSGS), terminal)
+        assert hit.cache_hit is True
+        assert hit.cached_prompt_tokens == 64
+        assert hit.model_reported == "MiniMax-Text-01-250321"
+
+    async def test_legacy_cache_entry_without_new_keys_rehydrates(self):
+        """旧格式条目(无这两个键)必须照常重建为 None,不得抛异常回源。"""
+        backend = InMemoryCache()
+        mw = _mw(backend)
+        key = build_cache_key("m", _MSGS, "proj", None)
+        legacy = {
+            "content": "legacy",
+            "thinking": "",
+            "model": "m",
+            "provider": "p",
+            "prompt_tokens": 1,
+            "completion_tokens": 2,
+            "latency_ms": 30,
+            "ttft_ms": 5.0,
+            "max_inter_token_ms": 2.0,
+            "cache_hit": False,
+            "call_id": "orig",
+            "source_name": "s1",
+            "cost": None,
+            "usage_source": "measured",
+        }
+        await backend.set(key, json.dumps(legacy), ttl_s=100)
+        terminal = _Terminal(_resp())
+        hit = await mw(ChatRequest(messages=_MSGS), terminal)
+        assert hit.content == "legacy" and terminal.calls == 0  # 真的走了缓存
+        assert hit.cached_prompt_tokens is None and hit.model_reported is None
+
+
 class _BrokenBackend:
     async def get(self, key):
         raise ConnectionError("redis down")

tests/unit/test_retry.py

@@ -194,6 +194,35 @@ class TestSuccessPath:
         assert (await limiter.source_stats("a")).tpm_used == 16
 
 
+class TestObservabilityPassthrough:
+    """issue #3: transport 采到的两个可观测字段必须原样上浮到 LLMResponse。"""
+
+    async def test_fields_reach_the_response(self):
+        result = TransportResult(
+            content="ok",
+            thinking="",
+            prompt_tokens=10,
+            completion_tokens=5,
+            usage_source="measured",
+            ttft_ms=12.0,
+            max_inter_token_ms=3.0,
+            raw={},
+            cached_prompt_tokens=64,
+            model_reported="MiniMax-Text-01-250321",
+        )
+        mw, *_ = _harness([_src("a")], [result])
+        resp = await mw(_REQ)
+        assert resp.cached_prompt_tokens == 64
+        assert resp.model_reported == "MiniMax-Text-01-250321"
+        # model 仍是配置别名: 真实版本是旁证,不顶替溯源主字段
+        assert resp.model == "m"
+
+    async def test_absent_fields_stay_none(self):
+        mw, *_ = _harness([_src("a")], [_ok()])
+        resp = await mw(_REQ)
+        assert resp.cached_prompt_tokens is None and resp.model_reported is None
+
+
 class TestRetryAndFailover:
     async def test_transient_switches_source_then_succeeds(self):
         mw, _, _, transport, sleep, _ = _harness(