fix: 文生图连接测试 size 1024x1024 + 媒体端点智能推导 + 图像/视频模型 failover 路由(默认模型第一顺位)

backend/python/app/api/admin/models.py

@@ -869,6 +869,9 @@ async def test_model_connection(
 
     model_type = _detect_model_type(ai_model.capabilities)
     timeout = ai_model.timeout or 60
+    # 图像生成实际会出图，单张耗时较长；连接测试需给足超时，否则会误报"失败"
+    if model_type == "image":
+        timeout = max(min(ai_model.timeout or 60, 200), 120)
     headers = {
         "Authorization": f"Bearer {api_key}",
         "Content-Type": "application/json",
@@ -927,7 +930,7 @@ async def test_model_connection(
                     "model": ai_model.name,
                     "prompt": "a red circle",
                     "n": 1,
-                    "size": "256x256",
+                    "size": "1024x1024",
                 }
                 resp = await client.post(image_url, json=payload, headers=headers)
                 latency = int((time.time() - start) * 1000)

backend/python/app/api/chat_media.py

@@ -839,6 +839,86 @@ async def _agnes_post_json(api_url: str, headers: dict, payload: dict, timeout)
 
     return None, last_err
 
+
+def _media_api_url(ai_model, provider, media_kind: str) -> str:
+    """推导图像/视频生成地址，避免把 chat/completions 端点误用作媒体端点。
+
+    - 若模型 endpoint 已是对应的媒体端点(含 /images/generations 或 /videos)，直接使用；
+    - 否则从 chat endpoint 反推 base，再拼 /v1/images|videos/generations；
+    - 若 endpoint 为空，则回退供应商 api_base_url + 媒体路径。
+    """
+    suffix = "/v1/images/generations" if media_kind == "image" else "/v1/videos"
+    chat_suffixes = ["/v1/chat/completions", "/chat/completions"]
+    ep = (ai_model.endpoint or "").strip()
+    if ep:
+        if suffix in ep:
+            return ep
+        base = ep
+        for cs in chat_suffixes:
+            if base.endswith(cs):
+                base = base[: -len(cs)]
+                break
+        else:
+            if "/v1" in base:
+                base = base.rsplit("/v1", 1)[0]
+        return f"{base.rstrip('/')}{suffix}"
+    if provider and provider.api_base_url:
+        return f"{provider.api_base_url.rstrip('/')}{suffix}"
+    return ""
+
+def _build_media_route(db, capability: str, preferred_id: str = None):
+    """构造媒体生成模型路由顺序：
+    1) 按能力默认模型(后台"能力默认模型"或全局默认) 作为第一顺位
+    2) 调用方显式指定的模型(若不同于默认) 次位
+    3) 其余启用且具备该能力的模型，按 is_default 降序、created_at 升序 排列
+    去重后返回 AIModel 列表。
+    """
+    from ..models import AIModel as _AM
+
+    selected = []
+    seen = set()
+
+    def _add(m):
+        if m and m.id not in seen:
+            selected.append(m)
+            seen.add(m.id)
+
+    default_model = resolve_auto_model(capability, db)
+    if default_model:
+        _add(default_model)
+
+    if preferred_id:
+        pref = db.query(_AM).filter(_AM.id == preferred_id, _AM.is_enabled == True).first()
+        _add(pref)
+
+    others = db.query(_AM).filter(
+        _AM.is_enabled == True,
+        _AM.capabilities.op("JSON_CONTAINS")(_AM.capabilities, f'"{capability}"'),
+    ).order_by(_AM.is_default.desc(), _AM.created_at.asc()).all()
+    for m in others:
+        _add(m)
+
+    return selected
+
+
+async def _run_media_route(db, route, prompt, user_id, media_kind):
+    """依次尝试路由中的模型生成媒体；首个成功(非 ⚠️ 开头)即返回，否则尝试下一个。"""
+    last_err = None
+    for idx, m in enumerate(route, 1):
+        logger.info(f"[_run_media_route] ({idx}/{len(route)}) 尝试模型 {m.name} ({m.id})")
+        try:
+            res = await _generate_media(db, m, prompt, user_id)
+        except Exception as e:
+            last_err = f"模型 {m.name} 异常: {str(e)[:160]}"
+            logger.warning(f"[_run_media_route] 模型 {m.name} 异常: {e}")
+            continue
+        if res and not res.startswith("⚠️"):
+            return res
+        last_err = res
+        logger.warning(f"[_run_media_route] 模型 {m.name} 失败: {str(res)[:160]}")
+    return last_err or "⚠️ 所有模型均生成失败"
+
+
 async def _generate_media(db, ai_model, prompt: str, user_id: str = None) -> str:
 
 
@@ -880,6 +960,9 @@ async def _generate_media(db, ai_model, prompt: str, user_id: str = None) -> str
 
 
     timeout = ai_model.timeout or 120
+    # 单次媒体调用超时封顶：避免单个供应商长时间挂起拖垮整条生成链路；
+    # 多模型 failover 由 _generate_media_task 外层循环保证
+    call_timeout = min(timeout, 300 if "video" in caps else 180)
 
 
 
@@ -895,15 +978,7 @@ async def _generate_media(db, ai_model, prompt: str, user_id: str = None) -> str
 
 
 
-        api_url = ai_model.endpoint
+        api_url = _media_api_url(ai_model, provider, "image")
-
-
-
-        if not api_url:
-
-
-
-            api_url = f"{provider.api_base_url.rstrip('/')}/v1/images/generations" if provider else ""
 
 
 
@@ -951,7 +1026,7 @@ async def _generate_media(db, ai_model, prompt: str, user_id: str = None) -> str
 
 
 
-            "size": "1024x768",
+            "size": "1024x1024",
 
 
 
@@ -960,7 +1035,7 @@ async def _generate_media(db, ai_model, prompt: str, user_id: str = None) -> str
 
 
         async with span("media.agnes_call"):
-            resp, err = await _agnes_post_json(api_url, headers, payload, timeout)
+            resp, err = await _agnes_post_json(api_url, headers, payload, call_timeout)
 
 
 
@@ -992,7 +1067,7 @@ async def _generate_media(db, ai_model, prompt: str, user_id: str = None) -> str
 
 
 
-                resp2, _ = await _agnes_post_json(api_url, headers, payload, timeout)
+                resp2, _ = await _agnes_post_json(api_url, headers, payload, call_timeout)
 
 
 
@@ -1092,15 +1167,7 @@ async def _generate_media(db, ai_model, prompt: str, user_id: str = None) -> str
 
 
 
-        api_url = ai_model.endpoint
+        api_url = _media_api_url(ai_model, provider, "video")
-
-
-
-        if not api_url:
-
-
-
-            api_url = f"{provider.api_base_url.rstrip('/')}/v1/videos" if provider else ""
 
 
 
@@ -1169,7 +1236,7 @@ async def _generate_media(db, ai_model, prompt: str, user_id: str = None) -> str
 
 
         async with span("media.agnes_call"):
-            resp, err = await _agnes_post_json(api_url, headers, payload, timeout)
+            resp, err = await _agnes_post_json(api_url, headers, payload, call_timeout)
 
 
 
@@ -1197,7 +1264,7 @@ async def _generate_media(db, ai_model, prompt: str, user_id: str = None) -> str
 
 
 
-                resp2, _ = await _agnes_post_json(api_url, headers, payload, timeout)
+                resp2, _ = await _agnes_post_json(api_url, headers, payload, call_timeout)
 
 
 
@@ -1430,22 +1497,27 @@ async def _generate_media_task(ai_msg_id: str, ai_model_id: str, prompt: str, us
         logger.info(f"[_generate_media_task] 启动 media 生成 msg={ai_msg_id} model={ai_model_id} prompt={prompt[:60]!r}")
         caps = [c.lower() for c in (ai_model.capabilities or [])]
         is_video = "video" in caps
-        timeout_seconds = 300 if is_video else 180
+        media_kind = "video" if is_video else "image"
+
+        # 构造模型路由：默认模型第一顺位，之后按路由策略逐一尝试
+        route = _build_media_route(db, media_kind, ai_model_id)
+        if not route:
+            result = f"⚠️ 未找到可用的{'视频' if is_video else '图像'}模型，请在后台「大模型库」中启用具备该能力的模型。"
+        else:
+            _media_name = "视频" if is_video else "图像"
+            per_call = 300 if is_video else 180
+            route_timeout = min(per_call * len(route) + 30, 900 if is_video else 600)
             try:
                 result = await asyncio.wait_for(
-                _generate_media(db, ai_model, prompt, user_id),
+                    _run_media_route(db, route, prompt, user_id, media_kind),
-                timeout=timeout_seconds
+                    timeout=route_timeout,
                 )
-
-
-
             except asyncio.TimeoutError:
-            logger.warning(f"[_generate_media_task] media 生成超时 msg={ai_msg_id} is_video={is_video} timeout={timeout_seconds}s")
+                logger.warning(f"[_generate_media_task] media 路由全部超时 msg={ai_msg_id} is_video={is_video} timeout={route_timeout}s")
-            _media_name = "视频" if is_video else "图像"
+                result = f"⚠️ {_media_name}生成超时：已依次尝试 {len(route)} 个模型仍失败，请稍后重试。"
-            result = f"⚠️ 媒体生成超时：{_media_name}生成耗时超过 {timeout_seconds} 秒，请稍后重试。"
             except Exception as e:
-            logger.warning(f"[_generate_media_task] media 生成异常 msg={ai_msg_id}: {e}", exc_info=True)
+                logger.warning(f"[_generate_media_task] media 路由异常 msg={ai_msg_id}: {e}", exc_info=True)
-            result = f"⚠️ 媒体生成失败：{str(e)[:200]}"
+                result = f"⚠️ {_media_name}生成失败：{str(e)[:200]}"