AstrBot 4.7.3__tar.gz → 4.7.4__tar.gz

{astrbot-4.7.3 → astrbot-4.7.4}/.gitignore

@@ -48,3 +48,5 @@ astrbot.lock
 chroma
 venv/*
 pytest.ini
+AGENTS.md
+IFLOW.md

{astrbot-4.7.3 → astrbot-4.7.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: AstrBot
-Version: 4.7.3
+Version: 4.7.4
 Summary: Easy-to-use multi-platform LLM chatbot and development framework
 License-File: LICENSE
 Keywords: Astrbot,Astrbot Module,Astrbot Plugin

astrbot-4.7.4/astrbot/cli/__init__.py

@@ -0,0 +1 @@
+__version__ = "4.7.4"

{astrbot-4.7.3 → astrbot-4.7.4}/astrbot/core/agent/message.py

@@ -3,7 +3,7 @@
 
 from typing import Any, ClassVar, Literal, cast
 
-from pydantic import BaseModel, GetCoreSchemaHandler
+from pydantic import BaseModel, GetCoreSchemaHandler, model_validator
 from pydantic_core import core_schema
 
 
@@ -145,23 +145,39 @@ class Message(BaseModel):
         "tool",
     ]
 
-    content: str | list[ContentPart]
+    content: str | list[ContentPart] | None = None
     """The content of the message."""
 
+    tool_calls: list[ToolCall] | list[dict] | None = None
+    """The tool calls of the message."""
+
+    tool_call_id: str | None = None
+    """The ID of the tool call."""
+
+    @model_validator(mode="after")
+    def check_content_required(self):
+        # assistant + tool_calls is not None: allow content to be None
+        if self.role == "assistant" and self.tool_calls is not None:
+            return self
+
+        # other all cases: content is required
+        if self.content is None:
+            raise ValueError(
+                "content is required unless role='assistant' and tool_calls is not None"
+            )
+        return self
+
 
 class AssistantMessageSegment(Message):
     """A message segment from the assistant."""
 
     role: Literal["assistant"] = "assistant"
-    content: str | list[ContentPart] | None = None
-    tool_calls: list[ToolCall] | list[dict] | None = None
 
 
 class ToolCallMessageSegment(Message):
     """A message segment representing a tool call."""
 
     role: Literal["tool"] = "tool"
-    tool_call_id: str
 
 
 class UserMessageSegment(Message):

{astrbot-4.7.3 → astrbot-4.7.4}/astrbot/core/config/default.py

@@ -4,7 +4,7 @@ import os
 
 from astrbot.core.utils.astrbot_path import get_astrbot_data_path
 
-VERSION = "4.7.3"
+VERSION = "4.7.4"
 DB_PATH = os.path.join(get_astrbot_data_path(), "data_v4.db")
 
 # 默认配置
@@ -73,8 +73,14 @@ DEFAULT_CONFIG = {
         "coze_agent_runner_provider_id": "",
         "dashscope_agent_runner_provider_id": "",
         "unsupported_streaming_strategy": "realtime_segmenting",
+        "reachability_check": False,
         "max_agent_step": 30,
         "tool_call_timeout": 60,
+        "file_extract": {
+            "enable": False,
+            "provider": "moonshotai",
+            "moonshotai_api_key": "",
+        },
     },
     "provider_stt_settings": {
         "enable": False,
@@ -2068,6 +2074,20 @@ CONFIG_METADATA_2 = {
                     "tool_call_timeout": {
                         "type": "int",
                     },
+                    "file_extract": {
+                        "type": "object",
+                        "items": {
+                            "enable": {
+                                "type": "bool",
+                            },
+                            "provider": {
+                                "type": "string",
+                            },
+                            "moonshotai_api_key": {
+                                "type": "string",
+                            },
+                        },
+                    },
                 },
             },
             "provider_stt_settings": {
@@ -2402,6 +2422,36 @@ CONFIG_METADATA_3 = {
                     "provider_settings.enable": True,
                 },
             },
+            # "file_extract": {
+            #     "description": "文档解析能力 [beta]",
+            #     "type": "object",
+            #     "items": {
+            #         "provider_settings.file_extract.enable": {
+            #             "description": "启用文档解析能力",
+            #             "type": "bool",
+            #         },
+            #         "provider_settings.file_extract.provider": {
+            #             "description": "文档解析提供商",
+            #             "type": "string",
+            #             "options": ["moonshotai"],
+            #             "condition": {
+            #                 "provider_settings.file_extract.enable": True,
+            #             },
+            #         },
+            #         "provider_settings.file_extract.moonshotai_api_key": {
+            #             "description": "Moonshot AI API Key",
+            #             "type": "string",
+            #             "condition": {
+            #                 "provider_settings.file_extract.provider": "moonshotai",
+            #                 "provider_settings.file_extract.enable": True,
+            #             },
+            #         },
+            #     },
+            #     "condition": {
+            #         "provider_settings.agent_runner_type": "local",
+            #         "provider_settings.enable": True,
+            #     },
+            # },
             "others": {
                 "description": "其他配置",
                 "type": "object",
@@ -2496,6 +2546,11 @@ CONFIG_METADATA_3 = {
                         "description": "开启 TTS 时同时输出语音和文字内容",
                         "type": "bool",
                     },
+                    "provider_settings.reachability_check": {
+                        "description": "提供商可达性检测",
+                        "type": "bool",
+                        "hint": "/provider 命令列出模型时是否并发检测连通性。开启后会主动调用模型测试连通性，可能产生额外 token 消耗。",
+                    },
                 },
                 "condition": {
                     "provider_settings.enable": True,

{astrbot-4.7.3 → astrbot-4.7.4}/astrbot/core/message/components.py

@@ -722,7 +722,12 @@ class File(BaseMessageComponent):
         """下载文件"""
         download_dir = os.path.join(get_astrbot_data_path(), "temp")
         os.makedirs(download_dir, exist_ok=True)
-        file_path = os.path.join(download_dir, f"{uuid.uuid4().hex}")
+        if self.name:
+            name, ext = os.path.splitext(self.name)
+            filename = f"{name}_{uuid.uuid4().hex[:8]}{ext}"
+        else:
+            filename = f"{uuid.uuid4().hex}"
+        file_path = os.path.join(download_dir, filename)
         await download_file(self.url, file_path)
         self.file_ = os.path.abspath(file_path)
 

{astrbot-4.7.3 → astrbot-4.7.4}/astrbot/core/pipeline/process_stage/method/agent_sub_stages/internal.py

@@ -9,7 +9,7 @@ from astrbot.core import logger
 from astrbot.core.agent.tool import ToolSet
 from astrbot.core.astr_agent_context import AstrAgentContext
 from astrbot.core.conversation_mgr import Conversation
-from astrbot.core.message.components import Image
+from astrbot.core.message.components import File, Image, Reply
 from astrbot.core.message.message_event_result import (
     MessageChain,
     MessageEventResult,
@@ -22,6 +22,7 @@ from astrbot.core.provider.entities import (
     ProviderRequest,
 )
 from astrbot.core.star.star_handler import EventType, star_map
+from astrbot.core.utils.file_extract import extract_file_moonshotai
 from astrbot.core.utils.metrics import Metric
 from astrbot.core.utils.session_lock import session_lock_manager
 
@@ -56,6 +57,13 @@ class InternalAgentSubStage(Stage):
         self.show_reasoning = settings.get("display_reasoning_text", False)
         self.kb_agentic_mode: bool = conf.get("kb_agentic_mode", False)
 
+        file_extract_conf: dict = settings.get("file_extract", {})
+        self.file_extract_enabled: bool = file_extract_conf.get("enable", False)
+        self.file_extract_prov: str = file_extract_conf.get("provider", "moonshotai")
+        self.file_extract_msh_api_key: str = file_extract_conf.get(
+            "moonshotai_api_key", ""
+        )
+
         self.conv_manager = ctx.plugin_manager.context.conversation_manager
 
     def _select_provider(self, event: AstrMessageEvent):
@@ -114,6 +122,50 @@ class InternalAgentSubStage(Stage):
                 req.func_tool = ToolSet()
             req.func_tool.add_tool(KNOWLEDGE_BASE_QUERY_TOOL)
 
+    async def _apply_file_extract(
+        self,
+        event: AstrMessageEvent,
+        req: ProviderRequest,
+    ):
+        """Apply file extract to the provider request"""
+        file_paths = []
+        file_names = []
+        for comp in event.message_obj.message:
+            if isinstance(comp, File):
+                file_paths.append(await comp.get_file())
+                file_names.append(comp.name)
+            elif isinstance(comp, Reply) and comp.chain:
+                for reply_comp in comp.chain:
+                    if isinstance(reply_comp, File):
+                        file_paths.append(await reply_comp.get_file())
+                        file_names.append(reply_comp.name)
+        if not file_paths:
+            return
+        if not req.prompt:
+            req.prompt = "总结一下文件里面讲了什么？"
+        if self.file_extract_prov == "moonshotai":
+            if not self.file_extract_msh_api_key:
+                logger.error("Moonshot AI API key for file extract is not set")
+                return
+            file_contents = await asyncio.gather(
+                *[
+                    extract_file_moonshotai(file_path, self.file_extract_msh_api_key)
+                    for file_path in file_paths
+                ]
+            )
+        else:
+            logger.error(f"Unsupported file extract provider: {self.file_extract_prov}")
+            return
+
+        # add file extract results to contexts
+        for file_content, file_name in zip(file_contents, file_names):
+            req.contexts.append(
+                {
+                    "role": "system",
+                    "content": f"File Extract Results of user uploaded files:\n{file_content}\nFile Name: {file_name or 'Unknown'}",
+                },
+            )
+
     def _truncate_contexts(
         self,
         contexts: list[dict],
@@ -346,6 +398,17 @@ class InternalAgentSubStage(Stage):
 
                 event.set_extra("provider_request", req)
 
+            # fix contexts json str
+            if isinstance(req.contexts, str):
+                req.contexts = json.loads(req.contexts)
+
+            # apply file extract
+            if self.file_extract_enabled:
+                try:
+                    await self._apply_file_extract(event, req)
+                except Exception as e:
+                    logger.error(f"Error occurred while applying file extract: {e}")
+
             if not req.prompt and not req.image_urls:
                 return
 
@@ -356,10 +419,6 @@ class InternalAgentSubStage(Stage):
             # apply knowledge base feature
             await self._apply_kb(event, req)
 
-            # fix contexts json str
-            if isinstance(req.contexts, str):
-                req.contexts = json.loads(req.contexts)
-
             # truncate contexts to fit max length
             if req.contexts:
                 req.contexts = self._truncate_contexts(req.contexts)

{astrbot-4.7.3 → astrbot-4.7.4}/astrbot/core/platform/sources/aiocqhttp/aiocqhttp_platform_adapter.py

@@ -246,7 +246,13 @@ class AiocqhttpAdapter(Platform):
                     if m["data"].get("url") and m["data"].get("url").startswith("http"):
                         # Lagrange
                         logger.info("guessing lagrange")
-                        file_name = m["data"].get("file_name", "file")
+                        # 检查多个可能的文件名字段
+                        file_name = (
+                            m["data"].get("file_name", "")
+                            or m["data"].get("name", "")
+                            or m["data"].get("file", "")
+                            or "file"
+                        )
                         abm.message.append(File(name=file_name, url=m["data"]["url"]))
                     else:
                         try:
@@ -265,7 +271,14 @@ class AiocqhttpAdapter(Platform):
                                 )
                             if ret and "url" in ret:
                                 file_url = ret["url"]  # https
-                                a = File(name="", url=file_url)
+                                # 优先从 API 返回值获取文件名，其次从原始消息数据获取
+                                file_name = (
+                                    ret.get("file_name", "")
+                                    or ret.get("name", "")
+                                    or m["data"].get("file", "")
+                                    or m["data"].get("file_name", "")
+                                )
+                                a = File(name=file_name, url=file_url)
                                 abm.message.append(a)
                             else:
                                 logger.error(f"获取文件失败: {ret}")

{astrbot-4.7.3 → astrbot-4.7.4}/astrbot/core/platform/sources/dingtalk/dingtalk_adapter.py

@@ -250,7 +250,7 @@ class DingtalkPlatformAdapter(Platform):
 
     async def terminate(self):
         def monkey_patch_close():
-            raise Exception("Graceful shutdown")
+            raise KeyboardInterrupt("Graceful shutdown")
 
         self.client_.open_connection = monkey_patch_close
         await self.client_.websocket.close(code=1000, reason="Graceful shutdown")

{astrbot-4.7.3 → astrbot-4.7.4}/astrbot/core/platform/sources/telegram/tg_adapter.py

@@ -381,7 +381,9 @@ class TelegramPlatformAdapter(Platform):
                     f"Telegram document file_path is None, cannot save the file {file_name}.",
                 )
             else:
-                message.message.append(Comp.File(file=file_path, name=file_name))
+                message.message.append(
+                    Comp.File(file=file_path, name=file_name, url=file_path)
+                )
 
         elif update.message.video:
             file = await update.message.video.get_file()

{astrbot-4.7.3 → astrbot-4.7.4}/astrbot/core/provider/provider.py

@@ -1,5 +1,6 @@
 import abc
 import asyncio
+import os
 from collections.abc import AsyncGenerator
 
 from astrbot.core.agent.message import Message
@@ -11,6 +12,7 @@ from astrbot.core.provider.entities import (
     ToolCallsResult,
 )
 from astrbot.core.provider.register import provider_cls_map
+from astrbot.core.utils.astrbot_path import get_astrbot_path
 
 
 class AbstractProvider(abc.ABC):
@@ -43,6 +45,14 @@ class AbstractProvider(abc.ABC):
         )
         return meta
 
+    async def test(self):
+        """test the provider is a
+
+        raises:
+            Exception: if the provider is not available
+        """
+        ...
+
 
 class Provider(AbstractProvider):
     """Chat Provider"""
@@ -165,6 +175,12 @@ class Provider(AbstractProvider):
 
         return dicts
 
+    async def test(self, timeout: float = 45.0):
+        await asyncio.wait_for(
+            self.text_chat(prompt="REPLY `PONG` ONLY"),
+            timeout=timeout,
+        )
+
 
 class STTProvider(AbstractProvider):
     def __init__(self, provider_config: dict, provider_settings: dict) -> None:
@@ -177,6 +193,14 @@ class STTProvider(AbstractProvider):
         """获取音频的文本"""
         raise NotImplementedError
 
+    async def test(self):
+        sample_audio_path = os.path.join(
+            get_astrbot_path(),
+            "samples",
+            "stt_health_check.wav",
+        )
+        await self.get_text(sample_audio_path)
+
 
 class TTSProvider(AbstractProvider):
     def __init__(self, provider_config: dict, provider_settings: dict) -> None:
@@ -189,6 +213,9 @@ class TTSProvider(AbstractProvider):
         """获取文本的音频，返回音频文件路径"""
         raise NotImplementedError
 
+    async def test(self):
+        await self.get_audio("hi")
+
 
 class EmbeddingProvider(AbstractProvider):
     def __init__(self, provider_config: dict, provider_settings: dict) -> None:
@@ -211,6 +238,9 @@ class EmbeddingProvider(AbstractProvider):
         """获取向量的维度"""
         ...
 
+    async def test(self):
+        await self.get_embedding("astrbot")
+
     async def get_embeddings_batch(
         self,
         texts: list[str],
@@ -294,3 +324,8 @@ class RerankProvider(AbstractProvider):
     ) -> list[RerankResult]:
         """获取查询和文档的重排序分数"""
         ...
+
+    async def test(self):
+        result = await self.rerank("Apple", documents=["apple", "banana"])
+        if not result:
+            raise Exception("Rerank provider test failed, no results returned")

astrbot-4.7.4/astrbot/core/utils/file_extract.py

@@ -0,0 +1,23 @@
+from pathlib import Path
+
+from openai import AsyncOpenAI
+
+
+async def extract_file_moonshotai(file_path: str, api_key: str) -> str:
+    """Extract text from a file using Moonshot AI API"""
+    """
+    Args:
+        file_path: The path to the file to extract text from
+        api_key: The API key to use to extract text from the file
+    Returns:
+        The text extracted from the file
+    """
+    client = AsyncOpenAI(
+        api_key=api_key,
+        base_url="https://api.moonshot.cn/v1",
+    )
+    file_object = await client.files.create(
+        file=Path(file_path),
+        purpose="file-extract",  # type: ignore
+    )
+    return (await client.files.content(file_id=file_object.id)).text

{astrbot-4.7.3 → astrbot-4.7.4}/astrbot/dashboard/routes/config.py

@@ -18,11 +18,8 @@ from astrbot.core.config.i18n_utils import ConfigMetadataI18n
 from astrbot.core.core_lifecycle import AstrBotCoreLifecycle
 from astrbot.core.platform.register import platform_cls_map, platform_registry
 from astrbot.core.provider import Provider
-from astrbot.core.provider.entities import ProviderType
-from astrbot.core.provider.provider import RerankProvider
 from astrbot.core.provider.register import provider_registry
 from astrbot.core.star.star import star_registry
-from astrbot.core.utils.astrbot_path import get_astrbot_path
 
 from .route import Response, Route, RouteContext
 
@@ -356,169 +353,20 @@ class ConfigRoute(Route):
             f"Attempting to check provider: {status_info['name']} (ID: {status_info['id']}, Type: {status_info['type']}, Model: {status_info['model']})",
         )
 
-        if provider_capability_type == ProviderType.CHAT_COMPLETION:
-            try:
-                logger.debug(f"Sending 'Ping' to provider: {status_info['name']}")
-                response = await asyncio.wait_for(
-                    provider.text_chat(prompt="REPLY `PONG` ONLY"),
-                    timeout=45.0,
-                )
-                logger.debug(
-                    f"Received response from {status_info['name']}: {response}",
-                )
-                if response is not None:
-                    status_info["status"] = "available"
-                    response_text_snippet = ""
-                    if (
-                        hasattr(response, "completion_text")
-                        and response.completion_text
-                    ):
-                        response_text_snippet = (
-                            response.completion_text[:70] + "..."
-                            if len(response.completion_text) > 70
-                            else response.completion_text
-                        )
-                    elif hasattr(response, "result_chain") and response.result_chain:
-                        try:
-                            response_text_snippet = (
-                                response.result_chain.get_plain_text()[:70] + "..."
-                                if len(response.result_chain.get_plain_text()) > 70
-                                else response.result_chain.get_plain_text()
-                            )
-                        except Exception as _:
-                            pass
-                    logger.info(
-                        f"Provider {status_info['name']} (ID: {status_info['id']}) is available. Response snippet: '{response_text_snippet}'",
-                    )
-                else:
-                    status_info["error"] = (
-                        "Test call returned None, but expected an LLMResponse object."
-                    )
-                    logger.warning(
-                        f"Provider {status_info['name']} (ID: {status_info['id']}) test call returned None.",
-                    )
-
-            except asyncio.TimeoutError:
-                status_info["error"] = (
-                    "Connection timed out after 45 seconds during test call."
-                )
-                logger.warning(
-                    f"Provider {status_info['name']} (ID: {status_info['id']}) timed out.",
-                )
-            except Exception as e:
-                error_message = str(e)
-                status_info["error"] = error_message
-                logger.warning(
-                    f"Provider {status_info['name']} (ID: {status_info['id']}) is unavailable. Error: {error_message}",
-                )
-                logger.debug(
-                    f"Traceback for {status_info['name']}:\n{traceback.format_exc()}",
-                )
-
-        elif provider_capability_type == ProviderType.EMBEDDING:
-            try:
-                # For embedding, we can call the get_embedding method with a short prompt.
-                embedding_result = await provider.get_embedding("health_check")
-                if isinstance(embedding_result, list) and (
-                    not embedding_result or isinstance(embedding_result[0], float)
-                ):
-                    status_info["status"] = "available"
-                else:
-                    status_info["status"] = "unavailable"
-                    status_info["error"] = (
-                        f"Embedding test failed: unexpected result type {type(embedding_result)}"
-                    )
-            except Exception as e:
-                logger.error(
-                    f"Error testing embedding provider {provider_name}: {e}",
-                    exc_info=True,
-                )
-                status_info["status"] = "unavailable"
-                status_info["error"] = f"Embedding test failed: {e!s}"
-
-        elif provider_capability_type == ProviderType.TEXT_TO_SPEECH:
-            try:
-                # For TTS, we can call the get_audio method with a short prompt.
-                audio_result = await provider.get_audio("你好")
-                if isinstance(audio_result, str) and audio_result:
-                    status_info["status"] = "available"
-                else:
-                    status_info["status"] = "unavailable"
-                    status_info["error"] = (
-                        f"TTS test failed: unexpected result type {type(audio_result)}"
-                    )
-            except Exception as e:
-                logger.error(
-                    f"Error testing TTS provider {provider_name}: {e}",
-                    exc_info=True,
-                )
-                status_info["status"] = "unavailable"
-                status_info["error"] = f"TTS test failed: {e!s}"
-        elif provider_capability_type == ProviderType.SPEECH_TO_TEXT:
-            try:
-                logger.debug(
-                    f"Sending health check audio to provider: {status_info['name']}",
-                )
-                sample_audio_path = os.path.join(
-                    get_astrbot_path(),
-                    "samples",
-                    "stt_health_check.wav",
-                )
-                if not os.path.exists(sample_audio_path):
-                    status_info["status"] = "unavailable"
-                    status_info["error"] = (
-                        "STT test failed: sample audio file not found."
-                    )
-                    logger.warning(
-                        f"STT test for {status_info['name']} failed: sample audio file not found at {sample_audio_path}",
-                    )
-                else:
-                    text_result = await provider.get_text(sample_audio_path)
-                    if isinstance(text_result, str) and text_result:
-                        status_info["status"] = "available"
-                        snippet = (
-                            text_result[:70] + "..."
-                            if len(text_result) > 70
-                            else text_result
-                        )
-                        logger.info(
-                            f"Provider {status_info['name']} (ID: {status_info['id']}) is available. Response snippet: '{snippet}'",
-                        )
-                    else:
-                        status_info["status"] = "unavailable"
-                        status_info["error"] = (
-                            f"STT test failed: unexpected result type {type(text_result)}"
-                        )
-                        logger.warning(
-                            f"STT test for {status_info['name']} failed: unexpected result type {type(text_result)}",
-                        )
-            except Exception as e:
-                logger.error(
-                    f"Error testing STT provider {provider_name}: {e}",
-                    exc_info=True,
-                )
-                status_info["status"] = "unavailable"
-                status_info["error"] = f"STT test failed: {e!s}"
-        elif provider_capability_type == ProviderType.RERANK:
-            try:
-                assert isinstance(provider, RerankProvider)
-                await provider.rerank("Apple", documents=["apple", "banana"])
-                status_info["status"] = "available"
-            except Exception as e:
-                logger.error(
-                    f"Error testing rerank provider {provider_name}: {e}",
-                    exc_info=True,
-                )
-                status_info["status"] = "unavailable"
-                status_info["error"] = f"Rerank test failed: {e!s}"
-
-        else:
-            logger.debug(
-                f"Provider {provider_name} is not a Chat Completion or Embedding provider. Marking as available without test. Meta: {meta}",
-            )
+        try:
+            await provider.test()
             status_info["status"] = "available"
-            status_info["error"] = (
-                "This provider type is not tested and is assumed to be available."
+            logger.info(
+                f"Provider {status_info['name']} (ID: {status_info['id']}) is available.",
+            )
+        except Exception as e:
+            error_message = str(e)
+            status_info["error"] = error_message
+            logger.warning(
+                f"Provider {status_info['name']} (ID: {status_info['id']}) is unavailable. Error: {error_message}",
+            )
+            logger.debug(
+                f"Traceback for {status_info['name']}:\n{traceback.format_exc()}",
             )
 
         return status_info