feat: add aliyun quota fallback

config/model_profiles.py

@@ -1,9 +1,32 @@
 import os
+from pathlib import Path
 from typing import Optional
 
 def _env(name: str, default: str = "") -> str:
     return os.environ.get(name, default)
 
+def _env_optional(name: str) -> Optional[str]:
+    value = os.environ.get(name)
+    if value is None:
+        # 回退读取 .env（支持运行中更新）
+        env_path = Path(__file__).resolve().parents[1] / ".env"
+        if env_path.exists():
+            try:
+                for raw_line in env_path.read_text(encoding="utf-8").splitlines():
+                    line = raw_line.strip()
+                    if not line or line.startswith("#") or "=" not in line:
+                        continue
+                    key, val = line.split("=", 1)
+                    if key.strip() == name:
+                        value = val.strip().strip('"').strip("'")
+                        break
+            except Exception:
+                value = None
+    if value is None:
+        return None
+    value = value.strip()
+    return value or None
+
 
 # 模型上下文窗口（单位: token）
 CONTEXT_WINDOWS = {
@@ -19,6 +42,8 @@ CONTEXT_WINDOWS = {
 # 默认（Kimi）
 KIMI_BASE = _env("API_BASE_KIMI", _env("AGENT_API_BASE_URL", "https://api.moonshot.cn/v1"))
 KIMI_KEY = _env("API_KEY_KIMI", _env("AGENT_API_KEY", ""))
+KIMI_BASE_OFFICIAL = _env_optional("API_BASE_KIMI_OFFICIAL")
+KIMI_KEY_OFFICIAL = _env_optional("API_KEY_KIMI_OFFICIAL")
 KIMI_FAST_MODEL = _env("MODEL_KIMI_FAST", _env("AGENT_MODEL_ID", "kimi-k2-0905-preview"))
 KIMI_THINK_MODEL = _env("MODEL_KIMI_THINK", _env("AGENT_THINKING_MODEL_ID", "kimi-k2-thinking"))
 KIMI_25_MODEL = _env("MODEL_KIMI_25", "kimi-k2.5")
@@ -32,12 +57,16 @@ DEEPSEEK_THINK_MODEL = _env("MODEL_DEEPSEEK_THINK", "deepseek-reasoner")
 # Qwen
 QWEN_BASE = _env("API_BASE_QWEN", "https://dashscope.aliyuncs.com/compatible-mode/v1")
 QWEN_KEY = _env("API_KEY_QWEN", _env("DASHSCOPE_API_KEY", ""))
+QWEN_BASE_OFFICIAL = _env_optional("API_BASE_QWEN_OFFICIAL")
+QWEN_KEY_OFFICIAL = _env_optional("API_KEY_QWEN_OFFICIAL")
 QWEN_MAX_MODEL = _env("MODEL_QWEN_MAX", "qwen3-max")
 QWEN_VL_MODEL = _env("MODEL_QWEN_VL", "qwen3.5-plus")
 
 # MiniMax
 MINIMAX_BASE = _env("API_BASE_MINIMAX", "https://api.minimaxi.com/v1")
 MINIMAX_KEY = _env("API_KEY_MINIMAX", "")
+MINIMAX_BASE_OFFICIAL = _env_optional("API_BASE_MINIMAX_OFFICIAL")
+MINIMAX_KEY_OFFICIAL = _env_optional("API_KEY_MINIMAX_OFFICIAL")
 MINIMAX_MODEL = _env("MODEL_MINIMAX", "MiniMax-M2.5")
 
 
@@ -78,7 +107,7 @@ MODEL_PROFILES = {
             "model_id": KIMI_25_MODEL,
             "max_tokens": None,
             "context_window": CONTEXT_WINDOWS["kimi-k2.5"],
-            "extra_params": {"thinking": {"type": "enabled"}}
+            "extra_params": {"thinking": {"type": "enabled"}, "enable_thinking": True}
         },
         "supports_thinking": True,
         "fast_only": False,
@@ -204,6 +233,45 @@ def get_model_profile(key: str) -> dict:
     if key not in MODEL_PROFILES:
         raise ValueError(f"未知模型 key: {key}")
     profile = MODEL_PROFILES[key]
+    try:
+        from utils.aliyun_fallback import is_fallback_active
+    except Exception:
+        is_fallback_active = None
+
+    if is_fallback_active and is_fallback_active(key):
+        if key == "kimi-k2.5":
+            kimi_base_official = _env_optional("API_BASE_KIMI_OFFICIAL") or KIMI_BASE_OFFICIAL
+            kimi_key_official = _env_optional("API_KEY_KIMI_OFFICIAL") or KIMI_KEY_OFFICIAL
+            if kimi_base_official and kimi_key_official:
+                profile = dict(profile)
+                fast = dict(profile.get("fast") or {})
+                thinking = dict(profile.get("thinking") or fast)
+                fast.update({"base_url": kimi_base_official, "api_key": kimi_key_official})
+                thinking.update({"base_url": kimi_base_official, "api_key": kimi_key_official})
+                profile["fast"] = fast
+                profile["thinking"] = thinking
+        elif key == "qwen3-vl-plus":
+            qwen_base_official = _env_optional("API_BASE_QWEN_OFFICIAL") or QWEN_BASE_OFFICIAL
+            qwen_key_official = _env_optional("API_KEY_QWEN_OFFICIAL") or QWEN_KEY_OFFICIAL
+            if qwen_base_official and qwen_key_official:
+                profile = dict(profile)
+                fast = dict(profile.get("fast") or {})
+                thinking = dict(profile.get("thinking") or fast)
+                fast.update({"base_url": qwen_base_official, "api_key": qwen_key_official})
+                thinking.update({"base_url": qwen_base_official, "api_key": qwen_key_official})
+                profile["fast"] = fast
+                profile["thinking"] = thinking
+        elif key == "minimax-m2.5":
+            minimax_base_official = _env_optional("API_BASE_MINIMAX_OFFICIAL") or MINIMAX_BASE_OFFICIAL
+            minimax_key_official = _env_optional("API_KEY_MINIMAX_OFFICIAL") or MINIMAX_KEY_OFFICIAL
+            if minimax_base_official and minimax_key_official:
+                profile = dict(profile)
+                fast = dict(profile.get("fast") or {})
+                thinking = dict(profile.get("thinking") or fast)
+                fast.update({"base_url": minimax_base_official, "api_key": minimax_key_official})
+                thinking.update({"base_url": minimax_base_official, "api_key": minimax_key_official})
+                profile["fast"] = fast
+                profile["thinking"] = thinking
     # 基础校验：必须有 fast 段且有 key
     fast = profile.get("fast") or {}
     if not fast.get("api_key"):

scripts/mock_aliyun_quota_server.py

@@ -0,0 +1,40 @@
+from http.server import BaseHTTPRequestHandler, HTTPServer
+import json
+
+HOST = "0.0.0.0"
+PORT = 8899
+
+ERROR_MESSAGE = "hour allocated quota exceeded"
+
+class Handler(BaseHTTPRequestHandler):
+    def _send(self, code: int, payload: dict):
+        body = json.dumps(payload).encode("utf-8")
+        self.send_response(code)
+        self.send_header("Content-Type", "application/json; charset=utf-8")
+        self.send_header("Content-Length", str(len(body)))
+        self.end_headers()
+        self.wfile.write(body)
+
+    def do_POST(self):
+        # Consume request body to avoid broken pipe on clients
+        try:
+            length = int(self.headers.get("Content-Length", "0"))
+        except ValueError:
+            length = 0
+        if length:
+            _ = self.rfile.read(length)
+        payload = {
+            "error": {
+                "message": ERROR_MESSAGE,
+                "type": "quota_exceeded"
+            }
+        }
+        self._send(429, payload)
+
+    def log_message(self, format, *args):
+        return
+
+if __name__ == "__main__":
+    server = HTTPServer((HOST, PORT), Handler)
+    print(f"mock aliyun quota server running on http://{HOST}:{PORT}")
+    server.serve_forever()

server/chat_flow.py

@@ -505,6 +505,11 @@ async def handle_task_with_sender(terminal: WebTerminal, workspace: UserWorkspac
     context = web_terminal.build_context()
     messages = web_terminal.build_messages(context, message)
     tools = web_terminal.define_tools()
+    try:
+        profile = get_model_profile(getattr(web_terminal, "model_key", None) or "kimi-k2.5")
+        web_terminal.apply_model_profile(profile)
+    except Exception as exc:
+        debug_log(f"更新模型配置失败: {exc}")
 
     # === 上下文预算与安全校验（避免超出模型上下文） ===
     max_context_tokens = get_model_context_window(getattr(web_terminal, "model_key", None) or "kimi-k2.5")
@@ -559,6 +564,8 @@ async def handle_task_with_sender(terminal: WebTerminal, workspace: UserWorkspac
     
     # 设置最大迭代次数（API 可覆盖）
     max_iterations = getattr(web_terminal, "max_iterations_override", None) or MAX_ITERATIONS_PER_TASK
+    max_api_retries = 4
+    retry_delay_seconds = 10
     
     pending_append = None  # {"path": str, "tool_call_id": str, "buffer": str, ...}
     append_probe_buffer = ""
@@ -1199,6 +1206,25 @@ async def handle_task_with_sender(terminal: WebTerminal, workspace: UserWorkspac
             })
             maybe_mark_failure_from_message(web_terminal, message)
 
+    async def _wait_retry_delay(delay_seconds: int) -> bool:
+        """等待重试间隔，同时检查是否收到停止请求。"""
+        if delay_seconds <= 0:
+            return False
+        deadline = time.time() + delay_seconds
+        while time.time() < deadline:
+            client_stop_info = get_stop_flag(client_sid, username)
+            if client_stop_info:
+                stop_requested = client_stop_info.get('stop', False) if isinstance(client_stop_info, dict) else client_stop_info
+                if stop_requested:
+                    sender('task_stopped', {
+                        'message': '命令执行被用户取消',
+                        'reason': 'user_stop'
+                    })
+                    clear_stop_flag(client_sid, username)
+                    return True
+            await asyncio.sleep(0.2)
+        return False
+    
     for iteration in range(max_iterations):
         total_iterations += 1
         debug_log(f"\n--- 迭代 {iteration + 1}/{max_iterations} 开始 ---")
@@ -1293,6 +1319,33 @@ async def handle_task_with_sender(terminal: WebTerminal, workspace: UserWorkspac
         
         print(f"[API] 第{iteration + 1}次调用 (总工具调用: {total_tool_calls}/{MAX_TOTAL_TOOL_CALLS})")
         
+        api_error = None
+        for api_attempt in range(max_api_retries + 1):
+            api_error = None
+            if api_attempt > 0:
+                full_response = ""
+                tool_calls = []
+                current_thinking = ""
+                detected_tools = {}
+                last_usage_payload = None
+                in_thinking = False
+                thinking_started = False
+                thinking_ended = False
+                text_started = False
+                text_has_content = False
+                text_streaming = False
+                text_chunk_index = 0
+                last_text_chunk_time = None
+                chunk_count = 0
+                reasoning_chunks = 0
+                content_chunks = 0
+                tool_chunks = 0
+                append_break_triggered = False
+                append_result = {"handled": False}
+                modify_break_triggered = False
+                modify_result = {"handled": False}
+                last_finish_reason = None
+
             # 收集流式响应
             async for chunk in web_terminal.api_client.chat(messages, tools, stream=True):
                 chunk_count += 1
@@ -1315,6 +1368,10 @@ async def handle_task_with_sender(terminal: WebTerminal, workspace: UserWorkspac
                         clear_stop_flag(client_sid, username)
                         return
             
+                if isinstance(chunk, dict) and chunk.get("error"):
+                    api_error = chunk.get("error")
+                    break
+
                 # 先尝试记录 usage（有些平台会在最后一个 chunk 里携带 usage 但 choices 为空）
                 usage_info = chunk.get("usage")
                 if usage_info:
@@ -1687,6 +1744,58 @@ async def handle_task_with_sender(terminal: WebTerminal, workspace: UserWorkspac
             else:
                 debug_log("未获取到usage字段，跳过token统计更新")
         
+
+            if api_error:
+                error_message = ""
+                error_status = None
+                error_type = None
+                if isinstance(api_error, dict):
+                    error_status = api_error.get("status_code")
+                    error_type = api_error.get("error_type")
+                    error_message = api_error.get("error_message") or api_error.get("error_text") or ""
+                if not error_message:
+                    error_message = "API 请求失败"
+                # 若命中阿里云配额错误，立即写入状态并切换到官方 API
+                try:
+                    from utils.aliyun_fallback import compute_disabled_until, set_disabled_until
+                    disabled_until, reason = compute_disabled_until(error_message)
+                    if disabled_until and reason:
+                        set_disabled_until(getattr(web_terminal, "model_key", None) or "kimi-k2.5", disabled_until, reason)
+                        profile = get_model_profile(getattr(web_terminal, "model_key", None) or "kimi-k2.5")
+                        web_terminal.apply_model_profile(profile)
+                except Exception as exc:
+                    debug_log(f"处理阿里云配额回退失败: {exc}")
+                can_retry = (
+                    api_attempt < max_api_retries
+                    and not full_response
+                    and not tool_calls
+                    and not current_thinking
+                    and not pending_append
+                    and not pending_modify
+                )
+                sender('error', {
+                    'message': error_message,
+                    'status_code': error_status,
+                    'error_type': error_type,
+                    'retry': bool(can_retry),
+                    'retry_in': retry_delay_seconds if can_retry else None,
+                    'attempt': api_attempt + 1,
+                    'max_attempts': max_api_retries + 1
+                })
+                if can_retry:
+                    try:
+                        profile = get_model_profile(getattr(web_terminal, "model_key", None) or "kimi-k2.5")
+                        web_terminal.apply_model_profile(profile)
+                    except Exception as exc:
+                        debug_log(f"重试前更新模型配置失败: {exc}")
+                    cancelled = await _wait_retry_delay(retry_delay_seconds)
+                    if cancelled:
+                        return
+                    continue
+                _cancel_pending_tools(tool_calls)
+                return
+            break
+
         # 流结束后的处理
         debug_log(f"\n流结束统计:")
         debug_log(f"  总chunks: {chunk_count}")

static/src/composables/useLegacySocket.ts

@@ -1042,6 +1042,10 @@ export async function initializeLegacySocket(ctx: any) {
             if (!msg) {
                 return;
             }
+            if (msg.awaitingFirstContent) {
+                msg.awaitingFirstContent = false;
+                msg.generatingLabel = '';
+            }
             const action = {
                 id: data.id,
                 type: 'tool',
@@ -1405,7 +1409,10 @@ export async function initializeLegacySocket(ctx: any) {
             const msg = data?.message || '发生未知错误';
             const code = data?.status_code;
             const errType = data?.error_type;
-            ctx.addSystemMessage(`错误: ${msg}`);
+            const shouldRetry = Boolean(data?.retry);
+            const retryIn = Number(data?.retry_in) || 5;
+            const retryAttempt = Number(data?.attempt) || 1;
+            const retryMax = Number(data?.max_attempts) || retryAttempt;
             if (typeof ctx.uiPushToast === 'function') {
                 ctx.uiPushToast({
                     title: code ? `API错误 ${code}` : 'API错误',
@@ -1413,8 +1420,35 @@ export async function initializeLegacySocket(ctx: any) {
                     type: 'error',
                     duration: 6000
                 });
+                if (shouldRetry) {
+                    ctx.uiPushToast({
+                        title: '即将重试',
+                        message: `将在 ${retryIn} 秒后重试（第 ${retryAttempt}/${retryMax} 次）`,
+                        type: 'info',
+                        duration: Math.max(retryIn, 1) * 1000
+                    });
+                }
+            }
+            if (shouldRetry) {
+                // 错误后保持停止按钮态，用户可手动停止或等待自动重试
+                ctx.stopRequested = false;
+                ctx.taskInProgress = true;
+                ctx.streamingMessage = true;
+                return;
+            }
+
+            // 最后一次报错：恢复输入状态并清理提示动画
+            const msgIndex = typeof ctx.currentMessageIndex === 'number' ? ctx.currentMessageIndex : -1;
+            if (msgIndex >= 0 && Array.isArray(ctx.messages)) {
+                const currentMessage = ctx.messages[msgIndex];
+                if (currentMessage && currentMessage.role === 'assistant') {
+                    currentMessage.awaitingFirstContent = false;
+                    currentMessage.generatingLabel = '';
+                }
+            }
+            if (typeof ctx.chatClearThinkingLocks === 'function') {
+                ctx.chatClearThinkingLocks();
             }
-            // 仅标记当前流结束，避免状态错乱
             ctx.streamingMessage = false;
             ctx.stopRequested = false;
             ctx.taskInProgress = false;

utils/aliyun_fallback.py

@@ -0,0 +1,103 @@
+import json
+from datetime import datetime, timedelta, timezone
+from pathlib import Path
+from typing import Dict, Optional, Tuple
+
+
+FALLBACK_MODELS = {"qwen3-vl-plus", "kimi-k2.5", "minimax-m2.5"}
+STATE_PATH = Path(__file__).resolve().parents[1] / "data" / "aliyun_fallback_state.json"
+
+
+def _read_state() -> Dict:
+    if not STATE_PATH.exists():
+        return {"models": {}}
+    try:
+        data = json.loads(STATE_PATH.read_text(encoding="utf-8"))
+    except Exception:
+        return {"models": {}}
+    if not isinstance(data, dict):
+        return {"models": {}}
+    if "models" not in data or not isinstance(data["models"], dict):
+        data["models"] = {}
+    return data
+
+
+def _write_state(data: Dict) -> None:
+    STATE_PATH.parent.mkdir(parents=True, exist_ok=True)
+    STATE_PATH.write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
+
+
+def get_disabled_until(model_key: str) -> Optional[float]:
+    data = _read_state()
+    entry = (data.get("models") or {}).get(model_key) or {}
+    ts = entry.get("disabled_until")
+    try:
+        return float(ts) if ts is not None else None
+    except (TypeError, ValueError):
+        return None
+
+
+def is_fallback_active(model_key: str, now_ts: Optional[float] = None) -> bool:
+    if model_key not in FALLBACK_MODELS:
+        return False
+    now_ts = float(now_ts) if now_ts is not None else datetime.now(tz=timezone.utc).timestamp()
+    disabled_until = get_disabled_until(model_key)
+    return bool(disabled_until and disabled_until > now_ts)
+
+
+def set_disabled_until(model_key: str, disabled_until_ts: float, reason: str = "") -> None:
+    if model_key not in FALLBACK_MODELS:
+        return
+    data = _read_state()
+    models = data.setdefault("models", {})
+    models[model_key] = {
+        "disabled_until": float(disabled_until_ts),
+        "reason": reason,
+        "updated_at": datetime.now(tz=timezone.utc).timestamp(),
+    }
+    _write_state(data)
+
+
+def _next_monday_utc8(now: datetime) -> datetime:
+    # Monday = 0
+    weekday = now.weekday()
+    days_ahead = (7 - weekday) % 7
+    if days_ahead == 0:
+        days_ahead = 7
+    target = (now + timedelta(days=days_ahead)).replace(hour=0, minute=0, second=0, microsecond=0)
+    return target
+
+
+def _next_month_same_day_utc8(now: datetime) -> datetime:
+    year = now.year
+    month = now.month + 1
+    if month > 12:
+        month = 1
+        year += 1
+    # clamp day to last day of next month
+    if month == 12:
+        next_month = datetime(year + 1, 1, 1, tzinfo=now.tzinfo)
+    else:
+        next_month = datetime(year, month + 1, 1, tzinfo=now.tzinfo)
+    last_day = (next_month - timedelta(days=1)).day
+    day = min(now.day, last_day)
+    return datetime(year, month, day, 0, 0, 0, tzinfo=now.tzinfo)
+
+
+def compute_disabled_until(error_text: str) -> Tuple[Optional[float], Optional[str]]:
+    if not error_text:
+        return None, None
+    text = str(error_text).lower()
+    tz8 = timezone(timedelta(hours=8))
+    now = datetime.now(tz=tz8)
+
+    if "hour allocated quota exceeded" in text or "每 5 小时请求额度已用完" in text:
+        until = now + timedelta(hours=5)
+        return until.astimezone(timezone.utc).timestamp(), "hour_quota"
+    if "week allocated quota exceeded" in text or "每周请求额度已用完" in text:
+        until = _next_monday_utc8(now)
+        return until.astimezone(timezone.utc).timestamp(), "week_quota"
+    if "month allocated quota exceeded" in text or "每月请求额度已用完" in text:
+        until = _next_month_same_day_utc8(now)
+        return until.astimezone(timezone.utc).timestamp(), "month_quota"
+    return None, None

utils/api_client.py

@@ -6,9 +6,12 @@ import json
 import asyncio
 import base64
 import mimetypes
+import os
 from typing import List, Dict, Optional, AsyncGenerator, Any
 from pathlib import Path
 from datetime import datetime
+from pathlib import Path
+from typing import Tuple
 try:
     from config import (
         API_BASE_URL,
@@ -78,6 +81,73 @@ class DeepSeekClient:
         # 请求体落盘目录
         self.request_dump_dir = Path(__file__).resolve().parents[1] / "logs" / "api_requests"
         self.request_dump_dir.mkdir(parents=True, exist_ok=True)
+        self.debug_log_path = Path(__file__).resolve().parents[1] / "logs" / "api_debug.log"
+
+    def _maybe_mark_aliyun_quota(self, error_text: str) -> None:
+        if not error_text or not self.model_key:
+            return
+        try:
+            from utils.aliyun_fallback import compute_disabled_until, set_disabled_until
+        except Exception:
+            return
+        disabled_until, reason = compute_disabled_until(error_text)
+        if disabled_until and reason:
+            set_disabled_until(self.model_key, disabled_until, reason)
+            # 立即切换到官方 API（仅在有配置时）
+            base_env_key = None
+            key_env_key = None
+            if self.model_key == "kimi-k2.5":
+                base_env_key = "API_BASE_KIMI_OFFICIAL"
+                key_env_key = "API_KEY_KIMI_OFFICIAL"
+            elif self.model_key == "qwen3-vl-plus":
+                base_env_key = "API_BASE_QWEN_OFFICIAL"
+                key_env_key = "API_KEY_QWEN_OFFICIAL"
+            elif self.model_key == "minimax-m2.5":
+                base_env_key = "API_BASE_MINIMAX_OFFICIAL"
+                key_env_key = "API_KEY_MINIMAX_OFFICIAL"
+            if base_env_key and key_env_key:
+                official_base = self._resolve_env_value(base_env_key)
+                official_key = self._resolve_env_value(key_env_key)
+                if official_base and official_key:
+                    self.fast_api_config["base_url"] = official_base
+                    self.fast_api_config["api_key"] = official_key
+                    self.thinking_api_config["base_url"] = official_base
+                    self.thinking_api_config["api_key"] = official_key
+                    self.api_base_url = official_base
+                    self.api_key = official_key
+
+    def _debug_log(self, payload: Dict[str, Any]) -> None:
+        try:
+            entry = {
+                "ts": datetime.now().isoformat(),
+                **payload
+            }
+            self.debug_log_path.parent.mkdir(parents=True, exist_ok=True)
+            with self.debug_log_path.open("a", encoding="utf-8") as f:
+                f.write(json.dumps(entry, ensure_ascii=False) + "\n")
+        except Exception:
+            pass
+
+    def _resolve_env_value(self, name: str) -> Optional[str]:
+        value = os.environ.get(name)
+        if value is None:
+            env_path = Path(__file__).resolve().parents[1] / ".env"
+            if env_path.exists():
+                try:
+                    for raw_line in env_path.read_text(encoding="utf-8").splitlines():
+                        line = raw_line.strip()
+                        if not line or line.startswith("#") or "=" not in line:
+                            continue
+                        key, val = line.split("=", 1)
+                        if key.strip() == name:
+                            value = val.strip().strip('"').strip("'")
+                            break
+                except Exception:
+                    value = None
+        if value is None:
+            return None
+        value = value.strip()
+        return value or None
     
     def _print(self, message: str, end: str = "\n", flush: bool = False):
         """安全的打印函数，在Web模式下不输出"""
@@ -568,7 +638,10 @@ class DeepSeekClient:
                                 "error_text": error_text,
                                 "error_type": None,
                                 "error_message": None,
-                                "request_dump": str(dump_path)
+                                "request_dump": str(dump_path),
+                                "base_url": api_config.get("base_url"),
+                                "model_id": api_config.get("model_id"),
+                                "model_key": self.model_key
                             }
                             try:
                                 parsed = json.loads(error_text)
@@ -578,7 +651,20 @@ class DeepSeekClient:
                                     self.last_error_info["error_message"] = err.get("message")
                             except Exception:
                                 pass
-                            self._print(f"{OUTPUT_FORMATS['error']} API请求失败 ({response.status_code}): {error_text}")
+                            self._maybe_mark_aliyun_quota(error_text)
+                            self._debug_log({
+                                "event": "http_error_stream",
+                                "status_code": response.status_code,
+                                "error_text": error_text,
+                                "base_url": api_config.get("base_url"),
+                                "model_id": api_config.get("model_id"),
+                                "model_key": self.model_key,
+                                "request_dump": str(dump_path)
+                            })
+                            self._print(
+                                f"{OUTPUT_FORMATS['error']} API请求失败 ({response.status_code}): {error_text} "
+                                f"(base_url={api_config.get('base_url')}, model_id={api_config.get('model_id')})"
+                            )
                             self._mark_request_error(dump_path, response.status_code, error_text)
                             yield {"error": self.last_error_info}
                             return
@@ -607,7 +693,10 @@ class DeepSeekClient:
                             "error_text": error_text,
                             "error_type": None,
                             "error_message": None,
-                            "request_dump": str(dump_path)
+                            "request_dump": str(dump_path),
+                            "base_url": api_config.get("base_url"),
+                            "model_id": api_config.get("model_id"),
+                            "model_key": self.model_key
                         }
                         try:
                             parsed = response.json()
@@ -617,7 +706,20 @@ class DeepSeekClient:
                                 self.last_error_info["error_message"] = err.get("message")
                         except Exception:
                             pass
-                        self._print(f"{OUTPUT_FORMATS['error']} API请求失败 ({response.status_code}): {error_text}")
+                        self._maybe_mark_aliyun_quota(error_text)
+                        self._debug_log({
+                            "event": "http_error",
+                            "status_code": response.status_code,
+                            "error_text": error_text,
+                            "base_url": api_config.get("base_url"),
+                            "model_id": api_config.get("model_id"),
+                            "model_key": self.model_key,
+                            "request_dump": str(dump_path)
+                        })
+                        self._print(
+                            f"{OUTPUT_FORMATS['error']} API请求失败 ({response.status_code}): {error_text} "
+                            f"(base_url={api_config.get('base_url')}, model_id={api_config.get('model_id')})"
+                        )
                         self._mark_request_error(dump_path, response.status_code, error_text)
                         yield {"error": self.last_error_info}
                         return
@@ -632,8 +734,21 @@ class DeepSeekClient:
                 "error_text": "connect_error",
                 "error_type": "connection_error",
                 "error_message": "无法连接到API服务器",
-                "request_dump": str(dump_path)
+                "request_dump": str(dump_path),
+                "base_url": api_config.get("base_url"),
+                "model_id": api_config.get("model_id"),
+                "model_key": self.model_key
             }
+            self._maybe_mark_aliyun_quota(self.last_error_info.get("error_text"))
+            self._debug_log({
+                "event": "connect_error",
+                "status_code": None,
+                "error_text": "connect_error",
+                "base_url": api_config.get("base_url"),
+                "model_id": api_config.get("model_id"),
+                "model_key": self.model_key,
+                "request_dump": str(dump_path)
+            })
             self._mark_request_error(dump_path, error_text="connect_error")
             yield {"error": self.last_error_info}
         except httpx.TimeoutException:
@@ -643,8 +758,21 @@ class DeepSeekClient:
                 "error_text": "timeout",
                 "error_type": "timeout",
                 "error_message": "API请求超时",
-                "request_dump": str(dump_path)
+                "request_dump": str(dump_path),
+                "base_url": api_config.get("base_url"),
+                "model_id": api_config.get("model_id"),
+                "model_key": self.model_key
             }
+            self._maybe_mark_aliyun_quota(self.last_error_info.get("error_text"))
+            self._debug_log({
+                "event": "timeout",
+                "status_code": None,
+                "error_text": "timeout",
+                "base_url": api_config.get("base_url"),
+                "model_id": api_config.get("model_id"),
+                "model_key": self.model_key,
+                "request_dump": str(dump_path)
+            })
             self._mark_request_error(dump_path, error_text="timeout")
             yield {"error": self.last_error_info}
         except Exception as e:
@@ -654,8 +782,21 @@ class DeepSeekClient:
                 "error_text": str(e),
                 "error_type": "exception",
                 "error_message": str(e),
-                "request_dump": str(dump_path)
+                "request_dump": str(dump_path),
+                "base_url": api_config.get("base_url"),
+                "model_id": api_config.get("model_id"),
+                "model_key": self.model_key
             }
+            self._maybe_mark_aliyun_quota(self.last_error_info.get("error_text"))
+            self._debug_log({
+                "event": "exception",
+                "status_code": None,
+                "error_text": str(e),
+                "base_url": api_config.get("base_url"),
+                "model_id": api_config.get("model_id"),
+                "model_key": self.model_key,
+                "request_dump": str(dump_path)
+            })
             self._mark_request_error(dump_path, error_text=str(e))
             yield {"error": self.last_error_info}