mirror of
https://github.com/zhenxun-org/zhenxun_bot.git
synced 2026-10-14 00:20:06 +08:00
♻️ refactor(llm): 重构 LLM 服务架构,引入中间件与组件化适配器 (#2073)
检查bot是否运行正常 / bot check (push) Has been cancelled
CodeQL Code Security Analysis / Analyze (${{ matrix.language }}) (none, python) (push) Has been cancelled
Sequential Lint and Type Check / ruff-call (push) Has been cancelled
Release Drafter / Update Release Draft (push) Has been cancelled
Force Sync to Aliyun / sync (push) Has been cancelled
Update Version / update-version (push) Has been cancelled
Sequential Lint and Type Check / pyright-call (push) Has been cancelled
检查bot是否运行正常 / bot check (push) Has been cancelled
CodeQL Code Security Analysis / Analyze (${{ matrix.language }}) (none, python) (push) Has been cancelled
Sequential Lint and Type Check / ruff-call (push) Has been cancelled
Release Drafter / Update Release Draft (push) Has been cancelled
Force Sync to Aliyun / sync (push) Has been cancelled
Update Version / update-version (push) Has been cancelled
Sequential Lint and Type Check / pyright-call (push) Has been cancelled
* ♻️ refactor(llm): 重构 LLM 服务架构,引入中间件与组件化适配器 - 【重构】LLM 服务核心架构: - 引入中间件管道,统一处理请求生命周期(重试、密钥选择、日志、网络请求)。 - 适配器重构为组件化设计,分离配置映射、消息转换、响应解析和工具序列化逻辑。 - 移除 `with_smart_retry` 装饰器,其功能由中间件接管。 - 移除 `LLMToolExecutor`,工具执行逻辑集成到 `ToolInvoker`。 - 【功能】增强配置系统: - `LLMGenerationConfig` 采用组件化结构(Core, Reasoning, Visual, Output, Safety, ToolConfig)。 - 新增 `GenConfigBuilder` 提供语义化配置构建方式。 - 新增 `LLMEmbeddingConfig` 用于嵌入专用配置。 - `CommonOverrides` 迁移并更新至新配置结构。 - 【功能】强化工具系统: - 引入 `ToolInvoker` 实现更灵活的工具执行,支持回调与结构化错误。 - `function_tool` 装饰器支持动态 Pydantic 模型创建和依赖注入 (`ToolParam`, `RunContext`)。 - 平台原生工具支持 (`GeminiCodeExecution`, `GeminiGoogleSearch`, `GeminiUrlContext`)。 - 【功能】高级生成与嵌入: - `generate_structured` 方法支持 In-Context Validation and Repair (IVR) 循环和 AutoCoT (思维链) 包装。 - 新增 `embed_query` 和 `embed_documents` 便捷嵌入 API。 - `OpenAIImageAdapter` 支持 OpenAI 兼容的图像生成。 - `SmartAdapter` 实现模型名称智能路由。 - 【重构】消息与类型系统: - `LLMContentPart` 扩展支持更多模态和代码执行相关内容。 - `LLMMessage` 和 `LLMResponse` 结构更新,支持 `content_parts` 和思维链签名。 - 统一 `LLMErrorCode` 和用户友好错误消息,提供更详细的网络/代理错误提示。 - `pyproject.toml` 移除 `bilireq`,新增 `json_repair`。 - 【优化】日志与调试: - 引入 `DebugLogOptions`,提供细粒度日志脱敏控制。 - 增强日志净化器,处理更多敏感数据和长字符串。 - 【清理】删除废弃模块: - `zhenxun/services/llm/memory.py` - `zhenxun/services/llm/executor.py` - `zhenxun/services/llm/config/presets.py` - `zhenxun/services/llm/types/content.py` - `zhenxun/services/llm/types/enums.py` - `zhenxun/services/llm/tools/__init__.py` - `zhenxun/services/llm/tools/manager.py` * 📦️ build(deps): 移除 bilireq 并添加 json_repair 依赖 * 🐛 (llm): 移除图片生成模型能力预检查 * ♻️ refactor(llm.session): 重构记忆系统以分离存储和策略 * 🐛 fix(reload_setting): 重载配置时清除LLM缓存 * ✨ feat(llm): 支持结构化生成函数接收 UniMessage * ✨ feat(search): 为搜索功能默认启用 Gemini Google Search 工具 * 🚨 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>
This commit is contained in:
co-authored by
webjoin111
pre-commit-ci[bot]
parent
e5b2a872d3
commit
c9f0a8b9d9
@@ -13,15 +13,19 @@ from zhenxun.services.log import logger
|
||||
from zhenxun.utils.pydantic_compat import dump_json_safely
|
||||
|
||||
from .config import validate_override_params
|
||||
from .config.providers import AI_CONFIG_GROUP, PROVIDERS_CONFIG_KEY, get_ai_config
|
||||
from .config.generation import LLMGenerationConfig
|
||||
from .config.providers import (
|
||||
AI_CONFIG_GROUP,
|
||||
PROVIDERS_CONFIG_KEY,
|
||||
get_ai_config,
|
||||
get_llm_config,
|
||||
)
|
||||
from .core import http_client_manager, key_store
|
||||
from .service import LLMModel
|
||||
from .types import LLMErrorCode, LLMException, ModelDetail, ProviderConfig
|
||||
from .types.capabilities import get_model_capabilities
|
||||
|
||||
DEFAULT_MODEL_NAME_KEY = "default_model_name"
|
||||
PROXY_KEY = "proxy"
|
||||
TIMEOUT_KEY = "timeout"
|
||||
|
||||
_model_cache: dict[str, tuple[LLMModel, float]] = {}
|
||||
_cache_ttl = 3600
|
||||
@@ -39,7 +43,8 @@ def parse_provider_model_string(name_str: str | None) -> tuple[str | None, str |
|
||||
|
||||
|
||||
def _make_cache_key(
|
||||
provider_model_name: str | None, override_config: dict | None
|
||||
provider_model_name: str | None,
|
||||
override_config: dict | LLMGenerationConfig | None,
|
||||
) -> str:
|
||||
"""生成缓存键"""
|
||||
config_str = (
|
||||
@@ -115,11 +120,12 @@ def get_default_api_base_for_type(api_type: str) -> str | None:
|
||||
"""根据API类型获取默认的API基础地址"""
|
||||
default_api_bases = {
|
||||
"openai": "https://api.openai.com",
|
||||
"deepseek": "https://api.deepseek.com",
|
||||
"deepseek": "https://api.deepseek.com/beta",
|
||||
"zhipu": "https://open.bigmodel.cn",
|
||||
"gemini": "https://generativelanguage.googleapis.com",
|
||||
"openrouter": "https://openrouter.ai/api",
|
||||
"general_openai_compat": None,
|
||||
"smart": None,
|
||||
"openai_responses": None,
|
||||
}
|
||||
|
||||
return default_api_bases.get(api_type)
|
||||
@@ -244,7 +250,7 @@ def list_embedding_models() -> list[dict[str, Any]]:
|
||||
|
||||
async def get_model_instance(
|
||||
provider_model_name: str | None = None,
|
||||
override_config: dict[str, Any] | None = None,
|
||||
override_config: dict[str, Any] | LLMGenerationConfig | None = None,
|
||||
) -> LLMModel:
|
||||
"""
|
||||
根据 'ProviderName/ModelName' 字符串获取并实例化 LLMModel (异步版本)
|
||||
@@ -303,21 +309,20 @@ async def get_model_instance(
|
||||
|
||||
model_detail_found.is_embedding_model = capabilities.is_embedding_model
|
||||
|
||||
ai_config = get_ai_config()
|
||||
global_proxy_setting = ai_config.get(PROXY_KEY)
|
||||
llm_config = get_llm_config()
|
||||
client_settings = llm_config.client_settings
|
||||
default_timeout = (
|
||||
provider_config_found.timeout
|
||||
if provider_config_found.timeout is not None
|
||||
else 180
|
||||
else client_settings.timeout
|
||||
)
|
||||
global_timeout_setting = ai_config.get(TIMEOUT_KEY, default_timeout)
|
||||
|
||||
config_for_http_client = ProviderConfig(
|
||||
name=provider_config_found.name,
|
||||
api_key=provider_config_found.api_key,
|
||||
models=provider_config_found.models,
|
||||
timeout=global_timeout_setting,
|
||||
proxy=global_proxy_setting,
|
||||
timeout=default_timeout,
|
||||
proxy=client_settings.proxy,
|
||||
api_base=provider_config_found.api_base,
|
||||
api_type=provider_config_found.api_type,
|
||||
openai_compat=provider_config_found.openai_compat,
|
||||
|
||||
Reference in New Issue
Block a user