v2.0.1：修复推理型模型(Qwen3/DeepSeek reasoning_content)误报未收到输出+连接测试按连通判定+采样失败不中断+流式超时放宽60s/300s

tester.py

@@ -21,6 +21,7 @@ class TestRunner(threading.Thread):
         self.start_wall = time.time()
         self.ratio = None
         self.samples = []
+        self.last_error = None
 
     def request_cancel(self):
         self.cancel_flag = True
@@ -97,14 +98,26 @@ class TestRunner(threading.Thread):
                 except StopRequested:
                     raise
                 except ProviderError as e:
+                    # 单次采样失败：记录并继续后续采样，不让整个测试中断
+                    self.last_error = str(e)
                     self.log("ERROR", "[%d tok] 采样 %d/%d 失败: %s" % (L, i, n, e))
                     self.samples.append({"run_index": i, "context_length": L, "ok": False, "error": str(e)})
                     db.add_run(self.test_id, i, {}, str(e), context_length=L)
-                    raise e
 
         summary = self._make_summary()
-        db.update_status(self.test_id, "done", summary=summary)
-        self.log("INFO", "═══ 测试完成 ═══")
+        ok_count = summary.get("samples_ok") or 0
+        fail_count = summary.get("samples_total", 0) - ok_count
+        if ok_count:
+            db.update_status(self.test_id, "done", summary=summary,
+                             error=("%d 次采样失败：%s" % (fail_count, self.last_error)) if fail_count else "")
+            self.log("INFO", "═══ 测试完成 ═══")
+            if fail_count:
+                self.log("WARN", "共 %d 次采样失败（最后错误：%s）" % (fail_count, self.last_error))
+        else:
+            db.update_status(self.test_id, "error", summary=summary,
+                             error=self.last_error or "所有采样均失败")
+            self.log("ERROR", "所有采样均失败，测试标记为 error（最后错误：%s）" % (self.last_error or "未知"))
+            return
         self.log("INFO", "汇总: 平均首字 %.1f ms | 平均预填充 %.1f tok/s | 平均解码 %.1f tok/s"
                  % (summary.get("avg_ttft_ms") or 0,
                     summary.get("avg_prefill_speed") or 0,