fix(viral-video): 修复call_llm传list bug改client.chat_completion + timeout调优fast15/pro30 (80103f8c)

apps/worker/worker_app/tasks/viral_video.py

@@ -421,10 +421,14 @@ def _step_intent_parsing(job: ViralVideoJob, image_analysis: dict) -> dict:
             render_system_prompt,
             render_user_prompt,
         )
-        from packages.shared.ai_service import call_llm
+        from packages.shared.ai_client import get_doubao_client
     except ImportError:
         return {"intent": "推广产品", "key_messages": ["产品亮点"], "tone": "专业", "suggested_title": ""}
 
+    _llm_client = get_doubao_client()
+    if not _llm_client.is_available:
+        return {"intent": "推广产品", "key_messages": ["产品亮点"], "tone": "专业", "suggested_title": ""}
+
     products_summary = ""
     products = (image_analysis or {}).get("products", []) or []
     for p in products:
@@ -479,13 +483,13 @@ def _step_intent_parsing(job: ViralVideoJob, image_analysis: dict) -> dict:
     for _m, _lbl in [(_fast, "fast"), (_pro, "pro-fallback")]:
         try:
             logger.info("[爆款视频] 意图解析 model=%s label=%s", _m, _lbl)
-            raw = call_llm(
+            raw = _llm_client.chat_completion(
                 [{"role": "system", "content": system}, {"role": "user", "content": user}],
                 temperature=0.4,
                 max_tokens=1024,
                 model=_m,
                 timeout=60,
-            )  # #2180: 意图解析 LLM 实测需更长响应，原25s太紧
+            )  # #2180/#2215: 直接用 client.chat_completion 传 messages list，不再走 call_llm 字符串包装
             if not raw:
                 continue
             parsed = _parse(raw)
@@ -825,10 +829,14 @@ def _step_script_generation(job: ViralVideoJob, intent: dict, image_analysis: di
             GLOBAL_CONSTRAINTS,
             NEGATIVE_RULES,
         )
-        from packages.shared.ai_service import call_llm
+        from packages.shared.ai_client import get_doubao_client
     except ImportError:
         return _fallback_script(job)
 
+    _llm_client2 = get_doubao_client()
+    if not _llm_client2.is_available:
+        return _fallback_script(job)
+
     products_summary = _build_products_summary(image_analysis)
     dur = max(5, min(30, int(getattr(job, "duration", 15) or 15)))
 
@@ -864,7 +872,7 @@ def _step_script_generation(job: ViralVideoJob, intent: dict, image_analysis: di
 
     def _try_gen(model: str, temp: float, max_tok: int, label: str, tmo: int = 25):
         logger.info("[爆款视频] 编导脚本生成 model=%s label=%s timeout=%d", model, label, tmo)
-        raw = call_llm(
+        raw = _llm_client2.chat_completion(
             [{"role": "system", "content": system_tpl}, {"role": "user", "content": user}],
             temperature=temp,
             max_tokens=max_tok,

apps/worker/worker_app/tasks/vision/_prompt.py

@@ -1,7 +1,14 @@
 # -*- coding: utf-8 -*-
-"""V2 prompt 解析：优先读后台 viral_video_prompt_templates 配置，30s TTL 热加载；
-DB 不可用/读到默认XML模板时，fallback 到硬编码 JSON schema prompt。
+"""V2 prompt 解析：优先读后台 viral_video_prompt_templates 表（prompt_type='image_analysis'
+且 is_active=true），30s TTL 热加载；DB 无有效记录/异常时，fallback 到纯硬编码 JSON schema prompt。
+
+规则（简单直接，不做字符串匹配判断）：
+- DB 有 is_active=true 的 image_analysis 记录（含种子默认XML和用户修改后的版本）：
+  * system = DB.system_prompt + JSON_SCHEMA_APPEND（追加完整JSON字段schema，覆盖XML等其他输出格式要求）
+  * user   = DB.user_prompt_template 渲染后使用；渲染后为空则用硬编码默认
+- DB 无记录/连接异常/返回空：system/user 全部用纯硬编码 JSON schema prompt
 """
+
 from __future__ import annotations
 
 import logging
@@ -11,9 +18,9 @@ from typing import Any
 
 logger = logging.getLogger(__name__)
 
-# ---- 默认硬编码 prompt（DB 不可用或读到默认XML模板时使用） ----
+# ---- 纯硬编码 JSON schema（DB 无有效配置时全量使用） ----
 
-DEFAULT_FAST_SYSTEM = (
+_FAST_JSON_SCHEMA = (
     "你是图片结构化识别器。严格按下方 JSON schema 返回一个对象，不要任何解释、"
     "不要markdown、不要代码块、不要前后缀文字。字段值不确定时填 null 或空数组。\n"
     "{\n"
@@ -39,12 +46,13 @@ DEFAULT_FAST_SYSTEM = (
     '  "pattern": "图案，如纯色/条纹/波点/格子/印花/碎花/Logo等",\n'
     '  "colors": ["主色数组"],\n'
     '  "mood": "整体氛围/情绪，如清新/活力/高级/温暖/冷峻/甜美/复古等"\n'
-    "}"
+    "}\n\n"
+    "你必须只返回一个合法的JSON对象，不要输出任何其他文字、解释、XML标签或markdown。"
 )
 DEFAULT_FAST_USER = "识别这张图片的人物穿搭与主体信息，只返回JSON对象。"
 
-DEFAULT_PRO_SYSTEM = (
-    "你是图片分析专家。严格按下方 JSON schema 返回一个对象，不要解释、不要markdown、不要代码块。\n"
+_PRO_JSON_SCHEMA = (
+    "你是图片分析专家。严格按下方 JSON schema 返回一个对象，不要解释、不要markdown、不要代码块、不要XML标签。\n"
     "{\n"
     '  "has_person": true/false,\n'
     '  "gender": "男"/"女"/null,\n'
@@ -60,51 +68,98 @@ DEFAULT_PRO_SYSTEM = (
     '  "product_name": "产品名，非产品图填null",\n'
     '  "brand": "品牌，无则null",\n'
     '  "key_features": ["核心特征数组，3-6个短语"]\n'
-    "}"
+    "}\n\n"
+    "你必须只返回一个合法的JSON对象，不要输出任何其他文字、解释、XML标签或markdown。"
 )
 DEFAULT_PRO_USER = "分析这张图片，返回符合schema的JSON。"
 
-# 用户自定义 prompt 末尾追加的硬约束
-_JSON_TAIL_FAST = "\n\n你必须只返回一个合法的JSON对象，不要输出任何其他文字、解释或markdown。"
-_JSON_TAIL_PRO = "\n\n你必须只返回一个合法的JSON对象，不要输出任何其他文字、解释或markdown。"
+# DB 配置存在时，追加在用户 system_prompt 末尾的JSON schema约束
+_FAST_JSON_APPEND = (
+    "\n\n【输出格式要求】无论上文如何要求，最终你必须只返回一个合法的JSON对象，"
+    "严格包含以下字段（字段值不确定时填null或空数组）：\n"
+    "{\n"
+    '  "has_person": true/false,\n'
+    '  "gender": "男"/"女"/null,\n'
+    '  "age_range": "儿童"/"青少年"/"青年"/"中年"/"老年"/null,\n'
+    '  "upper_wear": "上装款式字符串",\n'
+    '  "upper_color": "上装主色",\n'
+    '  "lower_wear": "下装款式（穿连衣裙时填null）",\n'
+    '  "lower_color": "下装主色",\n'
+    '  "dress_color": "连衣裙主色（穿连衣裙时填）",\n'
+    '  "accessories": ["配饰数组"],\n'
+    '  "hairstyle": "发型",\n'
+    '  "expression": "表情",\n'
+    '  "pose": "姿势",\n'
+    '  "scene": "场景",\n'
+    '  "style": "风格",\n'
+    '  "has_product": true/false,\n'
+    '  "category": "产品类目：服饰/鞋包/美妆/数码/食品/家居/配饰/母婴/非产品图",\n'
+    '  "product_name": "产品名称，非产品图填null",\n'
+    '  "brand": "品牌或文字标识，无则null",\n'
+    '  "material": "材质",\n'
+    '  "pattern": "图案",\n'
+    '  "colors": ["主色数组"],\n'
+    '  "mood": "整体氛围"\n'
+    "}\n"
+    "不要输出任何其他文字、解释、XML标签或markdown。"
+)
 
-# 默认模板特征头（用于识别是否是内置XML模板）
-_DEFAULT_XML_MARKER = "你是电商商品视觉分析师"
+_PRO_JSON_APPEND = (
+    "\n\n【输出格式要求】无论上文如何要求，最终你必须只返回一个合法的JSON对象，"
+    "严格包含以下字段（字段值不确定时填null或空数组）：\n"
+    "{\n"
+    '  "has_person": true/false,\n'
+    '  "gender": "男"/"女"/null,\n'
+    '  "age_range": "儿童"/"青少年"/"青年"/"中年"/"老年"/null,\n'
+    '  "outfit": "整体穿着描述（含颜色款式）",\n'
+    '  "hair": "发型发色",\n'
+    '  "pose": "姿势",\n'
+    '  "expression": "表情",\n'
+    '  "scene": "场景",\n'
+    '  "mood": "氛围",\n'
+    '  "has_product": true/false,\n'
+    '  "category": "类目：服饰/鞋包/美妆/数码/食品/家居/配饰/母婴/非产品图",\n'
+    '  "product_name": "产品名，非产品图填null",\n'
+    '  "brand": "品牌，无则null",\n'
+    '  "key_features": ["核心特征3-6个短语"]\n'
+    "}\n"
+    "不要输出任何其他文字、解释、XML标签或markdown。"
+)
 
 _cache_lock = threading.Lock()
 _cache: dict[str, tuple[float, Any]] = {}
 _CACHE_TTL = 30.0
 
 
-def _load_template() -> Any | None:
-    """从DB读image_analysis模板，失败返回None。"""
+def _load_db_template() -> Any | None:
+    """直接查DB viral_video_prompt_templates 中 is_active=true 的 image_analysis 记录；
+    DB不可达/无记录/异常返回None。
+    复用 prompt_loader._load_from_db，它只查DB不做DEFAULT_TEMPLATES fallback，
+    返回None表示DB无记录或异常。"""
     try:
-        from packages.application.viral_video.prompt_loader import get_template
-        return get_template("image_analysis")
+        from packages.application.viral_video.prompt_loader import _load_from_db
+
+        return _load_from_db("image_analysis")
     except Exception as e:
-        logger.warning("[vision.v2] 读取后台prompt配置失败: %s", e)
+        logger.warning("[vision.v2] 查询DB prompt配置失败: %s", e)
         return None
 
 
-def _is_custom(template: Any) -> bool:
-    """判断读到的模板是不是用户自定义的（不是内置默认XML长prompt）。"""
-    if not template:
-        return False
-    sp = getattr(template, "system_prompt", "") or ""
-    # 默认模板开头是"你是电商商品视觉分析师..."，XML格式，不适合qwen+JSON
-    if _DEFAULT_XML_MARKER in sp[:30]:
-        return False
-    # 其他有内容的system_prompt视为用户自定义
-    return bool(sp.strip())
+def _render_user(tpl: Any | None, default_user: str) -> str:
+    if not tpl:
+        return default_user
+    tpl_str = getattr(tpl, "user_prompt_template", "") or ""
+    if not tpl_str.strip():
+        return default_user
+    rendered = tpl_str.replace("{image_count}", "1").replace("{industry}", "通用").replace("{image_urls}", "").strip()
+    return rendered or default_user
 
 
 def resolve_fast_prompt() -> tuple[str, str]:
-    """返回 (system_prompt, user_prompt) 给 qwen3.8-flash fast 路径。"""
     return _resolve("fast")
 
 
 def resolve_pro_prompt() -> tuple[str, str]:
-    """返回 (system_prompt, user_prompt) 给 qwen3.7-plus fallback 路径。"""
     return _resolve("pro")
 
 
@@ -116,32 +171,31 @@ def _resolve(kind: str) -> tuple[str, str]:
         if hit and now - hit[0] < _CACHE_TTL:
             return hit[1]
 
-    default_sys = DEFAULT_FAST_SYSTEM if kind == "fast" else DEFAULT_PRO_SYSTEM
+    default_sys = _FAST_JSON_SCHEMA if kind == "fast" else _PRO_JSON_SCHEMA
     default_user = DEFAULT_FAST_USER if kind == "fast" else DEFAULT_PRO_USER
-    tail = _JSON_TAIL_FAST if kind == "fast" else _JSON_TAIL_PRO
+    append = _FAST_JSON_APPEND if kind == "fast" else _PRO_JSON_APPEND
 
     sys_prompt = default_sys
     usr_prompt = default_user
     try:
-        tpl = _load_template()
-        if _is_custom(tpl):
-            custom_sys = (getattr(tpl, "system_prompt", "") or "").strip()
-            custom_user_tpl = getattr(tpl, "user_prompt_template", "") or ""
-            if custom_sys:
-                sys_prompt = custom_sys + tail
-            if custom_user_tpl:
-                # V2 是单图调用，简单替换几个常用占位符；缺键原样保留
-                usr_prompt = (custom_user_tpl
-                              .replace("{image_count}", "1")
-                              .replace("{industry}", "通用")
-                              .replace("{image_urls}", "")
-                              .strip())
-                if not usr_prompt:
-                    usr_prompt = default_user
-            logger.info("[vision.v2] 使用后台自定义prompt (kind=%s version=%s)",
-                        kind, getattr(tpl, "version", "?"))
+        tpl = _load_db_template()
+        if tpl is not None:
+            db_sys = (getattr(tpl, "system_prompt", "") or "").strip()
+            if db_sys:
+                sys_prompt = db_sys + append
+                usr_prompt = _render_user(tpl, default_user)
+                logger.info(
+                    "[vision.v2] 使用DB image_analysis prompt (kind=%s version=%s sys_len=%d)",
+                    kind,
+                    getattr(tpl, "version", "?"),
+                    len(db_sys),
+                )
+            else:
+                logger.debug("[vision.v2] DB image_analysis system_prompt为空，使用默认JSON (kind=%s)", kind)
+        else:
+            logger.debug("[vision.v2] DB无image_analysis记录/不可达，使用默认JSON prompt (kind=%s)", kind)
     except Exception as e:
-        logger.warning("[vision.v2] 解析后台prompt失败，使用默认: %s", e)
+        logger.warning("[vision.v2] 解析DB prompt异常，使用默认: %s", e)
 
     with _cache_lock:
         _cache[cache_key] = (now, (sys_prompt, usr_prompt))

apps/worker/worker_app/tasks/vision/fast_path.py

@@ -23,10 +23,10 @@ logger = logging.getLogger(__name__)
 
 # 超时（可通过环境变量覆盖）
 _IMG_WORKERS = int(os.environ.get("VISION_V2_IMG_WORKERS", "8"))
-_FAST_TIMEOUT = float(os.environ.get("VISION_V2_FAST_TIMEOUT", "12"))
-_FAST_JSON_TIMEOUT = float(os.environ.get("VISION_V2_FAST_JSON_TIMEOUT", "12"))
+_FAST_TIMEOUT = float(os.environ.get("VISION_V2_FAST_TIMEOUT", "15"))
+_FAST_JSON_TIMEOUT = float(os.environ.get("VISION_V2_FAST_JSON_TIMEOUT", "15"))
 _OCR_TIMEOUT = float(os.environ.get("VISION_V2_OCR_TIMEOUT", "6"))
-_PRO_TIMEOUT = float(os.environ.get("VISION_V2_PRO_TIMEOUT", "25"))
+_PRO_TIMEOUT = float(os.environ.get("VISION_V2_PRO_TIMEOUT", "30"))
 
 _FALLBACK_RESULT = {
     "name": "未识别",

apps/worker/worker_app/tasks/vision/vlm_fallback.py

@@ -25,7 +25,7 @@ logger = logging.getLogger(__name__)
 
 _BASE_URL = "https://dashscope.aliyuncs.com/compatible-mode/v1"
 _PRO_MODEL = "qwen3.7-plus"
-_DEFAULT_TIMEOUT = 25
+_DEFAULT_TIMEOUT = 30
 _DEFAULT_MAX_TOKENS = 800
 
 
@@ -131,10 +131,13 @@ def call_pro_vlm(
         "model": _PRO_MODEL,
         "messages": [
             {"role": "system", "content": system_prompt},
-            {"role": "user", "content": [
-                {"type": "image_url", "image_url": {"url": img_url}},
-                {"type": "text", "text": user_prompt},
-            ]},
+            {
+                "role": "user",
+                "content": [
+                    {"type": "image_url", "image_url": {"url": img_url}},
+                    {"type": "text", "text": user_prompt},
+                ],
+            },
         ],
         "temperature": 0.3,
         "max_tokens": _DEFAULT_MAX_TOKENS,
@@ -165,8 +168,11 @@ def call_pro_vlm(
             reasoning_tokens = ctd.get("reasoning_tokens", 0)
         logger.info(
             "[vision.v2] pro 完成 model=%s elapsed=%.1fs in=%d out=%d reasoning=%d",
-            _PRO_MODEL, elapsed,
-            usage.get("prompt_tokens", 0), usage.get("completion_tokens", 0), reasoning_tokens,
+            _PRO_MODEL,
+            elapsed,
+            usage.get("prompt_tokens", 0),
+            usage.get("completion_tokens", 0),
+            reasoning_tokens,
         )
         s = raw.strip()
         if s.startswith("```"):

apps/worker/worker_app/tasks/vision/vlm_fast_json.py

@@ -27,7 +27,7 @@ logger = logging.getLogger(__name__)
 # DashScope OpenAI 兼容 endpoint
 _BASE_URL = "https://dashscope.aliyuncs.com/compatible-mode/v1"
 _FAST_MODEL = "qwen3.8-flash"
-_DEFAULT_TIMEOUT = 12
+_DEFAULT_TIMEOUT = 15
 _DEFAULT_MAX_TOKENS = 350
 
 
@@ -102,7 +102,9 @@ def call_fast_json(
             )
             elapsed = time.time() - t0
         if resp.status_code != 200:
-            logger.warning("[vision.v2] fast_json HTTP %d elapsed=%.1fs body=%s", resp.status_code, elapsed, resp.text[:200])
+            logger.warning(
+                "[vision.v2] fast_json HTTP %d elapsed=%.1fs body=%s", resp.status_code, elapsed, resp.text[:200]
+            )
             return None
         data = resp.json()
         raw = (data.get("choices") or [{}])[0].get("message", {}).get("content")
@@ -116,8 +118,11 @@ def call_fast_json(
             reasoning_tokens = ctd.get("reasoning_tokens", 0)
         logger.info(
             "[vision.v2] fast_json 完成 model=%s elapsed=%.1fs in=%d out=%d reasoning=%d",
-            _FAST_MODEL, elapsed,
-            usage.get("prompt_tokens", 0), usage.get("completion_tokens", 0), reasoning_tokens,
+            _FAST_MODEL,
+            elapsed,
+            usage.get("prompt_tokens", 0),
+            usage.get("completion_tokens", 0),
+            reasoning_tokens,
         )
         text = _strip_code_fence(raw)
         lpos, r = text.find("{"), text.rfind("}")
@@ -133,7 +138,10 @@ def call_fast_json(
             return None
         logger.info(
             "[vision.v2] fast_json 完成 elapsed=%.1fs has_person=%s has_product=%s category=%s",
-            elapsed, obj.get("has_person"), obj.get("has_product"), obj.get("category"),
+            elapsed,
+            obj.get("has_person"),
+            obj.get("has_product"),
+            obj.get("category"),
         )
         return obj
     except Exception as e: