♻️ refactor(core): 重构 AI 能力与定时任务调度系统 (#2148)

* ♻️ refactor(core): 重构 AI 能力与定时任务调度系统 - 【AI 能力与工具】重构 Capability 注册与管理机制，引入 CapabilityManager 统一管理 - 移除全局能力注册表，改用声明式装饰器 `@capability` 进行解耦注册 - 重构工具解析器链，使用统一的 BaseToolResolver 代替原有的多个特定解析器 - 增强工具查询过滤，支持通配符匹配、工具箱过滤和排除标签 - 【定时任务调度】重构定时任务管理器，引入 SchedulerRegistry 统一管理任务元数据 - 引入 JobConfig 聚合定时任务配置，支持用户维度的定时任务调度 - 重构执行分发器，支持并发限制、串行间隔和随机延迟打散 - 【运行上下文】引入 ScheduledDeps 以支持后台和定时任务环境下的依赖注入 - 优化 RunContext，支持从定时任务上下文快速构造，并提供 emit 辅助方法 - 【日志与监控】引入 AILoggerProxy，实现 AI 各模块的专属日志输出 - 将各模块的全局 logger 替换为对应的模块专属日志代理 - 【其他优化】修复 Pydantic V1 兼容层中 model_validator 的装饰器兼容性问题 - 在非交互式环境（如定时任务）中自动隐藏 HITL 交互工具以节省 Token * ♻️ refactor(core): 优化内部导入路径并提升 Pydantic 兼容性 - 【重构】将 `services/ai` 模块内的绝对导入重构为相对导入，优化包结构 - 【重构】移除不必要的 `if TYPE_CHECKING` 保护，通过 `from __future__ import annotations` 直接导入类型 - 【清理】清理 `core/messages/types.py` 中未使用的 `AssistantContentUnion` 等联合类型定义 - 【优化】在 `utils/pydantic_compat.py` 中新增 `model_rebuild` 兼容函数，统一 Pydantic V1/V2 的模型重建逻辑 - 【优化】将部分函数内部的延迟导入提升至模块顶部，规范代码结构 * ♻️ refactor(imports): 优化导入路径为相对导入并清理冗余导入 - 【重构】将 AI 服务相关模块中的绝对导入路径修改为相对导入，提升模块内聚性与可移植性 - 【清理】移除多处函数内部或类方法中未使用的冗余导入，避免循环引用和资源浪费 - 【格式化】微调部分工具装饰器和返回语句的格式与尾随逗号 * 🚨 auto fix by pre-commit hooks --------- Co-authored-by: webjoin111 <455457521@qq.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2026-10-22 20:50:04 +08:00 · 2026-07-10 09:14:06 +08:00
parent 0b32d69c9c
commit 922d092650
132 changed files with 2372 additions and 1972 deletions
@@ -13,7 +13,7 @@ from .glm import GLMAdapter
 from .jina import JinaAdapter
 from .mimo import MiMoAdapter
 from .minimax import MiniMaxAdapter
-from .openai import OpenAIAdapter, OpenAICompatAdapter
+from .openai import OpenAIAdapter, OpenAICompatAdapter, OpenAIResponsesAdapter
 from .openrouter import OpenRouterAdapter

 LLMAdapterFactory.initialize()
@@ -30,6 +30,7 @@ __all__ = [
    "MiniMaxAdapter",
    "OpenAIAdapter",
    "OpenAICompatAdapter",
+    "OpenAIResponsesAdapter",
    "OpenRouterAdapter",
    "RequestData",
    "ResponseData",
@@ -47,11 +47,11 @@ from zhenxun.services.ai.core.messages import (
    ThoughtPart,
 )
 from zhenxun.services.ai.core.models import ModelIdentity
-from zhenxun.services.log import logger
+from zhenxun.services.ai.utils.logger import log_llm as logger
 from zhenxun.utils.log_sanitizer import sanitize_for_logging

 if TYPE_CHECKING:
-    from zhenxun.services.ai.llm.adapters.handlers.base import (
+    from .handlers.base import (
        BaseAudioHandler,
        BaseEmbeddingHandler,
        BaseImageHandler,
@@ -496,8 +496,7 @@ class BaseAdapter(ABC):
    async def parse_speech_response(
        self, identity: ModelIdentity, raw_response: httpx.Response
    ) -> AudioResponse:
-        """解析语音响应并委派给 `audio_handler`。
-        注意传入的是 httpx.Response 的 raw 对象"""
+        """解析语音响应并委派给 `audio_handler`"""
        if self.audio_handler:
            return await self.audio_handler.parse_speech_response(
                adapter=self, identity=identity, raw_response=raw_response
@@ -6,12 +6,13 @@ from zhenxun.services.ai.core.models import (
    ModelIdentity,
 )
 from zhenxun.services.ai.core.options import GenerationConfig
-from zhenxun.services.ai.llm.adapters.handlers.openai_handlers import (
+
+from .handlers.openai_handlers import (
    OpenAIConfigMapper,
    OpenAITextHandler,
    OpenAIToolSerializer,
 )
-from zhenxun.services.ai.llm.adapters.openai import OpenAICompatAdapter
+from .openai import OpenAICompatAdapter


 class DeepSeekToolSerializer(OpenAIToolSerializer):
@@ -84,21 +85,6 @@ class DeepSeekConfigMapper(OpenAIConfigMapper):
            if isinstance(rf, dict) and rf.get("type") == "json_schema":
                params["response_format"] = {"type": "json_object"}

-        if config.common.reasoning_effort:
-            effort = str(config.common.reasoning_effort).lower()
-            if effort == "none":
-                params["thinking"] = {"type": "disabled"}
-            else:
-                params["thinking"] = {"type": "enabled"}
-        elif (
-            hasattr(config, "deepseek_options")
-            and config.deepseek_options.thinking is not None
-        ):
-            if config.deepseek_options.thinking is True:
-                params["thinking"] = {"type": "enabled"}
-            elif config.deepseek_options.thinking is False:
-                params["thinking"] = {"type": "disabled"}
-
        return params


@@ -34,10 +34,11 @@ class LLMAdapterFactory:
        from .jina import JinaAdapter
        from .mimo import MiMoAdapter
        from .minimax import MiniMaxAdapter
-        from .openai import OpenAIAdapter
+        from .openai import OpenAIAdapter, OpenAIResponsesAdapter
        from .openrouter import OpenRouterAdapter

        cls.register_adapter(OpenAIAdapter())
+        cls.register_adapter(OpenAIResponsesAdapter())
        cls.register_adapter(OpenRouterAdapter())
        cls.register_adapter(DeepSeekAdapter())
        cls.register_adapter(JinaAdapter())
@@ -1,13 +1,14 @@
 from zhenxun.services.ai.core.messages import RerankRequest
 from zhenxun.services.ai.core.models import ModelIdentity
-from zhenxun.services.ai.llm.adapters.base import BaseAdapter, RequestData
-from zhenxun.services.ai.llm.adapters.handlers.openai_handlers import (
+
+from .base import BaseAdapter, RequestData
+from .handlers.openai_handlers import (
    OpenAIConfigMapper,
    OpenAIEmbeddingHandler,
    OpenAIRerankHandler,
    OpenAITextHandler,
 )
-from zhenxun.services.ai.llm.adapters.openai import OpenAICompatAdapter
+from .openai import OpenAICompatAdapter


 class GLMRerankHandler(OpenAIRerankHandler):
@@ -56,7 +56,9 @@ from zhenxun.services.ai.llm.adapters.base import (
    ResponseData,
    process_image_data,
 )
-from zhenxun.services.ai.llm.adapters.handlers.base import (
+from zhenxun.services.ai.utils.logger import log_llm as logger
+
+from .base import (
    BaseAudioHandler,
    BaseEmbeddingHandler,
    BaseImageHandler,
@@ -66,7 +68,6 @@ from zhenxun.services.ai.llm.adapters.handlers.base import (
    ResponseParser,
    ToolSerializer,
 )
-from zhenxun.services.log import logger


 class GeminiConfigMapper(ConfigMapper):
@@ -121,22 +122,19 @@ class GeminiConfigMapper(ConfigMapper):
                    fc_config["allowedFunctionNames"] = user_funcs
            params["toolConfig"] = {"functionCallingConfig": fc_config}

-        has_effort = bool(
-            config.common.reasoning_effort
-            and str(config.common.reasoning_effort).lower() != "none"
-        )
-        if (
-            has_effort
-            and capabilities
-            and capabilities.reasoning_mode == ReasoningMode.LEVEL
-        ):
-            thinking_config = params.setdefault("thinkingConfig", {})
+        if config.common.reasoning_effort and capabilities:
            effort = str(config.common.reasoning_effort).lower()
-
            if capabilities.reasoning_effort_map:
                effort = capabilities.reasoning_effort_map.get(effort, effort)

-            thinking_config["thinkingLevel"] = effort
+            if capabilities.reasoning_mode == ReasoningMode.LEVEL and effort != "none":
+                thinking_config = params.setdefault("thinkingConfig", {})
+                thinking_config["thinkingLevel"] = effort
+            elif (
+                capabilities.reasoning_mode == ReasoningMode.BUDGET and effort == "none"
+            ):
+                thinking_config = params.setdefault("thinkingConfig", {})
+                thinking_config["thinkingBudget"] = 0

        if config.gemini_options.include_thoughts is not None:
            thinking_config = params.setdefault("thinkingConfig", {})
@@ -829,10 +827,6 @@ class GeminiEmbeddingHandler(BaseEmbeddingHandler):
        url = f"{base_url}/v1beta/{api_model_name}:batchEmbedContents"
        headers = adapter.get_base_headers(api_key)

-        from zhenxun.services.ai.llm.adapters.handlers.gemini_handlers import (
-            GeminiMessageConverter,
-        )
-
        converter = GeminiMessageConverter()

        requests_payload = []
@@ -16,13 +16,13 @@ from zhenxun.services.ai.core.messages import (
 )
 from zhenxun.services.ai.core.models import (
    ModelCapabilities,
-    ModelDetail,
    ModelIdentity,
 )
-from zhenxun.services.ai.core.options import GenerationConfig, TTSConfig
+from zhenxun.services.ai.core.options import TTSConfig
 from zhenxun.services.ai.llm.adapters.base import BaseAdapter, RequestData
-from zhenxun.services.ai.llm.adapters.handlers.base import BaseAudioHandler
-from zhenxun.services.ai.llm.adapters.handlers.openai_handlers import (
+
+from .base import BaseAudioHandler
+from .openai_handlers import (
    OpenAIConfigMapper,
    OpenAIMessageConverter,
    OpenAITextHandler,
@@ -53,35 +53,6 @@ class MiMoToolSerializer(OpenAIToolSerializer):
        return res


-class MiMoConfigMapper(OpenAIConfigMapper):
-    """MiMo 配置映射器，处理深度思考参数差异"""
-
-    def map_config(
-        self,
-        config: GenerationConfig,
-        model_detail: ModelDetail | None = None,
-        capabilities: ModelCapabilities | None = None,
-    ) -> dict[str, Any]:
-        params = super().map_config(config, model_detail, capabilities)
-
-        if config.common.reasoning_effort:
-            effort = str(config.common.reasoning_effort).lower()
-            if effort == "none":
-                params["thinking"] = {"type": "disabled"}
-            else:
-                params["thinking"] = {"type": "enabled"}
-        elif (
-            hasattr(config, "deepseek_options")
-            and config.deepseek_options.thinking is not None
-        ):
-            if config.deepseek_options.thinking is True:
-                params["thinking"] = {"type": "enabled"}
-            elif config.deepseek_options.thinking is False:
-                params["thinking"] = {"type": "disabled"}
-
-        return params
-
-
 class MiMoMessageConverter(OpenAIMessageConverter):
    """MiMo 消息转换器，拦截处理特有的音视频多模态结构"""

@@ -141,7 +112,7 @@ class MiMoTextHandler(OpenAITextHandler):
        super().__init__(api_type=api_type)
        self.converter = MiMoMessageConverter(api_type=api_type)
        self.serializer = MiMoToolSerializer(api_type=api_type)
-        self.mapper = MiMoConfigMapper(api_type=api_type)
+        self.mapper = OpenAIConfigMapper(api_type=api_type)


 class MiMoAudioHandler(BaseAudioHandler):
@@ -53,7 +53,9 @@ from zhenxun.services.ai.llm.adapters.base import (
    ResponseData,
    process_image_data,
 )
-from zhenxun.services.ai.llm.adapters.handlers.base import (
+from zhenxun.services.ai.utils.logger import log_llm as logger
+
+from .base import (
    BaseAudioHandler,
    BaseEmbeddingHandler,
    BaseImageHandler,
@@ -64,7 +66,6 @@ from zhenxun.services.ai.llm.adapters.handlers.base import (
    ResponseParser,
    ToolSerializer,
 )
-from zhenxun.services.log import logger


 class OpenAIConfigMapper(ConfigMapper):
@@ -114,7 +115,13 @@ class OpenAIConfigMapper(ConfigMapper):
            if capabilities and capabilities.reasoning_effort_map:
                effort = capabilities.reasoning_effort_map.get(effort, effort)

-            if effort != "none":
+            if (
+                effort == "none"
+                and capabilities
+                and capabilities.supports_thinking_toggle
+            ):
+                params["thinking"] = {"type": "disabled"}
+            else:
                params["reasoning_effort"] = effort

        if isinstance(config.output.response_format, dict):
@@ -1165,45 +1172,3 @@ class OpenAIAudioHandler(BaseAudioHandler):
            usage=UsageInfo(),
            model_name=identity.model_name,
        )
-
-
-class CompositeOpenAITextHandler(BaseTextHandler):
-    """
-    OpenAI 复合文本对话处理器 (Composite Pattern)。
-    内部包装标准协议与 responses 协议 Handler，根据模型配置在请求时动态路由
-    """
-
-    def __init__(self, api_type: str = "openai"):
-        self.api_type = api_type
-        self._standard_handler = OpenAITextHandler(api_type=api_type)
-        self._responses_handler = OpenAIResponsesTextHandler(
-            api_type="openai_responses"
-        )
-
-    def _get_active_handler(self, identity: ModelIdentity) -> BaseTextHandler:
-        current_api_type = identity.api_type
-        if current_api_type == "openai_responses":
-            return self._responses_handler
-        return self._standard_handler
-
-    async def prepare_text_request(
-        self,
-        adapter: BaseAdapter,
-        identity: ModelIdentity,
-        api_key: str,
-        request: ChatRequest,
-    ) -> RequestData:
-        handler = self._get_active_handler(identity)
-        return await handler.prepare_text_request(adapter, identity, api_key, request)
-
-    def parse_text_response(
-        self,
-        adapter: BaseAdapter,
-        identity: ModelIdentity,
-        response_json: dict[str, Any],
-        is_advanced: bool = False,
-    ) -> ResponseData:
-        handler = self._get_active_handler(identity)
-        return handler.parse_text_response(
-            adapter, identity, response_json, is_advanced
-        )
@@ -1,12 +1,14 @@
 from zhenxun.services.ai.core.messages import EmbeddingRequest
 from zhenxun.services.ai.core.models import ModelIdentity
 from zhenxun.services.ai.core.options import LLMEmbeddingConfig
-from zhenxun.services.ai.llm.adapters.base import BaseAdapter, RequestData
-from zhenxun.services.ai.llm.adapters.handlers.openai_handlers import (
+from zhenxun.services.ai.utils.logger import log_llm as logger
+
+from .base import BaseAdapter, RequestData
+from .handlers.openai_handlers import (
    OpenAIEmbeddingHandler,
    OpenAIRerankHandler,
 )
-from zhenxun.services.ai.llm.adapters.openai import OpenAICompatAdapter
+from .openai import OpenAICompatAdapter


 class JinaEmbeddingHandler(OpenAIEmbeddingHandler):
@@ -36,7 +38,6 @@ class JinaEmbeddingHandler(OpenAIEmbeddingHandler):
                TextPart,
                VideoPart,
            )
-            from zhenxun.services.log import logger

            for payload in batch.payloads:
                jina_content = []
@@ -1,12 +1,13 @@
 from zhenxun.services.ai.core.models import ModelIdentity
-from zhenxun.services.ai.llm.adapters.handlers.mimo_handlers import (
+
+from .handlers.mimo_handlers import (
    MiMoAudioHandler,
    MiMoTextHandler,
 )
-from zhenxun.services.ai.llm.adapters.handlers.openai_handlers import (
+from .handlers.openai_handlers import (
    OpenAIImageHandler,
 )
-from zhenxun.services.ai.llm.adapters.openai import OpenAICompatAdapter
+from .openai import OpenAICompatAdapter


 class MiMoAdapter(OpenAICompatAdapter):
@@ -19,9 +19,9 @@ from zhenxun.services.ai.core.models import (
    ModelIdentity,
 )
 from zhenxun.services.ai.core.options import GenerationConfig, TTSConfig
-from zhenxun.services.ai.llm.adapters.base import BaseAdapter, RequestData
-from zhenxun.services.ai.llm.adapters.handlers.base import BaseAudioHandler

+from .base import BaseAdapter, RequestData
+from .handlers.base import BaseAudioHandler
 from .handlers.openai_handlers import (
    OpenAIConfigMapper,
    OpenAIMessageConverter,
@@ -15,11 +15,12 @@ from .base import (
    RequestData,
 )
 from .handlers.openai_handlers import (
-    CompositeOpenAITextHandler,
    OpenAIAudioHandler,
    OpenAIEmbeddingHandler,
    OpenAIImageHandler,
    OpenAIRerankHandler,
+    OpenAIResponsesTextHandler,
+    OpenAITextHandler,
 )


@@ -83,12 +84,12 @@ class OpenAICompatAdapter(BaseAdapter):


 class OpenAIAdapter(OpenAICompatAdapter):
-    """OpenAI 系列适配器，统一装配文本/图像/嵌入/重排处理链。"""
+    """标准 OpenAI 系列适配器，统一装配文本/图像/嵌入/重排处理链。"""

    def __init__(self):
-        """初始化并挂载复合文本处理器与通用多模态处理器。"""
+        """初始化并挂载标准文本处理器与通用多模态处理器。"""
        super().__init__()
-        self.text_handler = CompositeOpenAITextHandler(api_type=self.api_type)
+        self.text_handler = OpenAITextHandler(api_type=self.api_type)
        self.image_handler = OpenAIImageHandler()
        self.embedding_handler = OpenAIEmbeddingHandler()
        self.rerank_handler = OpenAIRerankHandler()
@@ -102,21 +103,35 @@ class OpenAIAdapter(OpenAICompatAdapter):
    @property
    def supported_api_types(self) -> list[str]:
        """支持的 API 类型及别名。"""
-        return [
-            "openai",
-            "openai_responses",
-        ]
+        return ["openai"]

    def get_chat_endpoint(self, identity: ModelIdentity) -> str:
        """返回聊天完成端点"""
-        current_api_type = identity.api_type
-
-        if current_api_type == "openai_responses":
-            return "/v1/responses"
-        if current_api_type == "doubao":
-            return "/api/v3/chat/completions"
        return "/v1/chat/completions"

    def get_embedding_endpoint(self, identity: ModelIdentity) -> str:
        """返回嵌入端点。"""
        return "/v1/embeddings"
+
+
+class OpenAIResponsesAdapter(OpenAICompatAdapter):
+    """OpenAI v1/responses 协议专用适配器"""
+
+    def __init__(self):
+        super().__init__()
+        self.text_handler = OpenAIResponsesTextHandler(api_type=self.api_type)
+        self.image_handler = OpenAIImageHandler()
+        self.embedding_handler = OpenAIEmbeddingHandler()
+        self.rerank_handler = OpenAIRerankHandler()
+        self.audio_handler = OpenAIAudioHandler()
+
+    @property
+    def api_type(self) -> str:
+        return "openai_responses"
+
+    @property
+    def supported_api_types(self) -> list[str]:
+        return ["openai_responses"]
+
+    def get_chat_endpoint(self, identity: ModelIdentity) -> str:
+        return "/v1/responses"
@@ -10,18 +10,19 @@ from zhenxun.services.ai.core.messages import (
    ThoughtPart,
 )
 from zhenxun.services.ai.core.models import ModelIdentity
-from zhenxun.services.ai.llm.adapters.base import (
+
+from .base import (
    BaseAdapter,
    RequestData,
    ResponseData,
    process_image_data,
 )
-from zhenxun.services.ai.llm.adapters.handlers.base import BaseImageHandler
-from zhenxun.services.ai.llm.adapters.handlers.openai_handlers import (
-    CompositeOpenAITextHandler,
+from .handlers.base import BaseImageHandler
+from .handlers.openai_handlers import (
    OpenAIMessageConverter,
+    OpenAITextHandler,
 )
-from zhenxun.services.ai.llm.adapters.openai import OpenAIAdapter
+from .openai import OpenAIAdapter


 class OpenRouterMessageConverter(OpenAIMessageConverter):
@@ -60,12 +61,12 @@ class OpenRouterMessageConverter(OpenAIMessageConverter):
        return openai_messages


-class OpenRouterTextHandler(CompositeOpenAITextHandler):
+class OpenRouterTextHandler(OpenAITextHandler):
    """OpenRouter 专有文本处理器，挂载专有 Converter"""

    def __init__(self, api_type: str = "openrouter"):
        super().__init__(api_type=api_type)
-        self._standard_handler.converter = OpenRouterMessageConverter(api_type=api_type)
+        self.converter = OpenRouterMessageConverter(api_type=api_type)


 class OpenRouterImageHandler(BaseImageHandler):