diff --git a/volc_consume.py b/volc_consume.py
index 5a912b0..248303a 100644
--- a/volc_consume.py
+++ b/volc_consume.py
@@ -31,8 +31,7 @@ import volc_limit_sync as vls
 # ==========================================
 # 🛠️ Configuration
 # ==========================================
-ARK_HOST = os.getenv("ARK_HOST", "ark.cn-beijing.volces.com")
-# 与 config.yaml 的 os.environ/HUOSHAN_BASE_URL 一致；用于生成与 LiteLLM 路径相同的 usage key
+# Ark endpoint 单源：URL 直接拼自 HUOSHAN_BASE_URL（与 config.yaml 同一 env）
 HUOSHAN_BASE_URL = os.getenv(
     "HUOSHAN_BASE_URL", "https://ark.cn-beijing.volces.com/api/v3"
 )
@@ -295,8 +294,9 @@ def calculate_plan_for_model(packages, model):
 # 🔌 Ark 直连请求
 # ==========================================
 def _send_ark(payload, timeout=120):
-    """直连 Ark Chat Completions（Bearer token，不经过 LiteLLM）。"""
-    url = f"https://{ARK_HOST}/api/v3/chat/completions"
+    """直连 Ark Chat Completions（Bearer token，不经过 LiteLLM）。
+    单源配置：endpoint 直接取 HUOSHAN_BASE_URL（与 config.yaml 同一 env），防 region 漂移。"""
+    url = f"{HUOSHAN_BASE_URL.rstrip('/')}/chat/completions"
     headers = {
         "Content-Type": "application/json",
         "Authorization": f"Bearer {ARK_API_KEY}",
@@ -305,10 +305,14 @@ def _send_ark(payload, timeout=120):
 
 
 def _build_payload(model, source_groups, order):
-    """构造消耗请求：日志语料 + 任务提示词，max_tokens 限制输出。"""
+    """构造消耗请求：日志语料 + 任务提示词。
+    模型参数与旧 MONITOR_TARGETS 实测配置一致：
+    - doubao-seed 系列 → max_completion_tokens + reasoning_effort minimal（火山方舟规范）
+    - 其他（glm/deepseek）→ max_tokens
+    """
     dynamic_input = generate_dynamic_payload(source_groups, order)
     tpl = random.choice(TASK_PROMPTS)
-    return {
+    payload = {
         "model": model,
         "messages": [
             {"role": "system", "content": tpl["sys"]},
@@ -318,8 +322,13 @@ def _build_payload(model, source_groups, order):
             },
         ],
         "stream": False,
-        "max_tokens": 1000,
     }
+    if model.startswith("doubao"):
+        payload["reasoning_effort"] = "minimal"
+        payload["max_completion_tokens"] = 1000
+    else:
+        payload["max_tokens"] = 1000
+    return payload
 
 
 # ==========================================
@@ -350,19 +359,21 @@ def _record_consumption(model, tokens):
 # ==========================================
 # 🎯 单模型消耗执行
 # ==========================================
-def run_consume_model(model, source_groups, order, dry_run=False):
+def run_consume_model(model, source_groups, order, packages=None, dry_run=False):
     """
     对单个监控模型执行"洗过期包"消耗。
     目标 = Σ窗口内包计划（均分×1.1/冲刺），clamp：
       - 采集上限：plan ≤ CONSUME_DAILY_CAP − 当日已消耗
       - 防扣费：plan ≤ 余额快照 − BUFFER
     停止条件（每轮检查）：daily_usage ≥ 2M / 余额快照−已烧 ≤ 0 / 已烧 ≥ plan
+    :param packages: 复用 run_consume_all 的一次拉包结果；None 时自行拉取
     """
-    try:
-        packages = vls.fetch_all_packages()
-    except Exception as e:
-        vls.log(f"❌ [{model}] 拉取资源包失败: {e}", level="ERROR")
-        return
+    if packages is None:
+        try:
+            packages = vls.fetch_all_packages()
+        except Exception as e:
+            vls.log(f"❌ [{model}] 拉取资源包失败: {e}", level="ERROR")
+            return
 
     plan, details, balance = calculate_plan_for_model(packages, model)
     for d in details:
@@ -401,12 +412,26 @@ def _run_requests(model, plan, balance_snapshot, source_groups, order):
     fail_count = 0
     deadline = time.time() + MAX_RUNTIME_SECONDS
 
-    # 速率估算：单次 ~4.3 万 token（输入 3-5.5 万字符 + 输出 ~1000）
+    # 速率三档（对齐旧 auto_consume run_stealthy_consume）：
+    #   任务轻松（单次间隔 > MAX_SLEEP_BASE）→ 正常模式 15-40s 伪装，不赶时间
+    #   任务极重（间隔 < 2s）→ 极速模式 1-3s（本场景 plan≤2M 实际不会触发）
+    #   其余 → 动态 ±5s
+    # 目标：23:00 触发、00:00 结算，1 小时内完成（plan=2M ≈ 47 次 × 27s ≈ 21 分钟）
     est_per_req = (MIN_INPUT_CHARS + MAX_INPUT_CHARS) / 2 + 1000
     est_requests = max(1, plan / est_per_req)
-    interval = int(min(60, max(2, 3600 / est_requests)))
-    cur_min = max(1, interval - 5)
-    cur_max = interval + 5
+    interval = int(3600 / est_requests)
+    if interval > MAX_SLEEP_BASE:
+        cur_min, cur_max = MIN_SLEEP_BASE, MAX_SLEEP_BASE
+        mode_str = "正常模式 🐢"
+    elif interval < 2:
+        cur_min, cur_max = 1, 3
+        mode_str = "极速模式 🐇"
+    else:
+        cur_min, cur_max = max(1, interval - 5), interval + 5
+        mode_str = f"动态调整 🚗 ({cur_min}~{cur_max}s)"
+    vls.log(
+        f"⚡ 速率控制: {mode_str} | 预计 {int(est_requests)} 次请求 (单次 ≈{int(est_per_req):,} token)"
+    )
 
     while burned < plan:
         if time.time() >= deadline:
@@ -483,9 +508,16 @@ def run_consume_all(dry_run=False):
         f"📄 语料来源: {', '.join(f'{k}({len(v)}行)' for k, v in source_groups.items())}"
     )
 
+    # 只拉一次资源包，全部模型复用（每模型独立 fetch 会重复分页 6 次）
+    try:
+        packages = vls.fetch_all_packages()
+    except Exception as e:
+        vls.log(f"❌ 拉取资源包失败: {e}", level="ERROR")
+        packages = []
+
     for model in models:
         try:
-            run_consume_model(model, source_groups, order, dry_run=dry_run)
+            run_consume_model(model, source_groups, order, packages=packages, dry_run=dry_run)
         except Exception as e:
             vls.log(f"❌ [{model}] 消耗任务异常: {e}\n{traceback.format_exc()}", level="ERROR")
 
diff --git a/volc_limit_sync.py b/volc_limit_sync.py
index 963c9fb..fabc4cb 100644
--- a/volc_limit_sync.py
+++ b/volc_limit_sync.py
@@ -91,7 +91,6 @@ REGION = "cn-beijing"
 
 # Daemon Config
 BUFFER = 300000  # User requested 30w buffer
-SYNC_INTERVAL = 60
 CHECK_INTERVAL = 10
 THRESHOLD = 300000
 
@@ -539,10 +538,8 @@ def restore_blocked_models():
     # Morning Window: 07:00 - 13:00
     if 7 <= beijing_hour < 13:
         interval = 1800  # 30 minutes
-        mode_str = "Morning/Window (30m)"
     else:
         interval = 14400  # 4 hours
-        mode_str = "Off-Peak (4h)"
 
     if now - last_restore_check < interval:
         return
@@ -806,7 +803,9 @@ class DailyLimitHandler(CustomLogger):
                 effective_limit = get_effective_limit(
                     clean_model, api_base, current_usage=current_total
                 )
-                display_limit = f"/{int(effective_limit):,}" if effective_limit else ""
+                limit_str = (
+                    f" | Limit: {int(effective_limit):,}" if effective_limit is not None else ""
+                )
 
                 # Get Dynamic Remaining for Log
                 dynamic_key = f"limit:dynamic:volcengine:remaining:{clean_model}"
@@ -829,10 +828,6 @@ class DailyLimitHandler(CustomLogger):
                         print(f"DEBUG: Dynamic key not found: {dynamic_key}")
 
                 key_display = key.split(":", 2)[-1]
-                # Display Limit clearly
-                limit_str = (
-                    f" | Limit: {int(effective_limit):,}" if effective_limit is not None else ""
-                )
                 log(
                     f"📊 [Usage] {key_display}: +{total_tokens} (Today: {current_total:,}{rem_display}{limit_str})",
                     level="INFO",
@@ -1419,7 +1414,7 @@ def active_monitor_loop():
                                 static_limit, stable_limit
                             )
                             print(
-                                f"DEBUG: {target} PeakPool={int(current_peak):,} | Usage={int(current_usage):,} | {format_limit_debug_fields(static_limit=static_limit, stable_limit=stable_limit, effective_limit=effective_limit)}",
+                                f"DEBUG: {target} Pool={int(total_pool):,} | Usage={int(current_usage):,} | {format_limit_debug_fields(static_limit=static_limit, stable_limit=stable_limit, effective_limit=effective_limit)}",
                                 flush=True,
                             )