feat(stream): add append-only streaming mode with flat cost

Add an append-only streaming path that feeds each audio chunk as a new
conversation turn, so nothing is ever recomputed: the KV grows by
append, no prefix is re-decoded and no audio is re-encoded. Per-step
cost becomes flat instead of growing with the segment (RTF 1.06 -> 0.26
on 62.6s of continuous speech), but accuracy requires ~8s chunks because
the audio encoder needs its 8s attention window, so text only appears
every 8s. The incremental mode stays the default.

新增追加式流式：每块音频作为一个新的对话轮追加，前缀不重算、旧音频不重
编码，单步成本不再随段落增长（连续 62.6s 语音 RTF 从 1.06 降到 0.26）。
但准确率要求 chunk≈8s，否则会被截断，所以出字粒度是 8s；增量式仍为默认。

tests/fakeasr.h

@@ -18,6 +18,7 @@ public:
 
     // 记录（供断言用）
     std::vector<std::string> prefixesSeen;
+    std::vector<std::string> turnsSeen;
     std::vector<size_t>      samplesSeen;
     int                      resets = 0;
 
@@ -52,6 +53,20 @@ public:
         return s;
     }
 
+    lc::AsrStreamStep streamAppendTurn(const float *, size_t nSamples, int) override
+    {
+        samplesSeen.push_back(nSamples);
+
+        lc::AsrStreamStep s;
+        s.ok = true;
+        if (call_ < scripted.size()) s.newText = scripted[call_];
+        ++call_;
+        turnsSeen.push_back(s.newText);
+        s.newTokens    = 1;
+        s.inferSeconds = 0.001;
+        return s;
+    }
+
     void streamReset() override { ++resets; }
 
     std::string dropLastTokens(const std::string & text, int dropLast) const override