AstrBot 4.10.5__py3-none-any.whl → 4.11.0__py3-none-any.whl

astrbot/core/agent/runners/tool_loop_agent_runner.py

@@ -25,6 +25,10 @@ from astrbot.core.provider.entities import (
 )
 from astrbot.core.provider.provider import Provider
 
+from ..context.compressor import ContextCompressor
+from ..context.config import ContextConfig
+from ..context.manager import ContextManager
+from ..context.token_counter import TokenCounter
 from ..hooks import BaseAgentRunHooks
 from ..message import AssistantMessageSegment, Message, ToolCallMessageSegment
 from ..response import AgentResponseData, AgentStats
@@ -47,10 +51,47 @@ class ToolLoopAgentRunner(BaseAgentRunner[TContext]):
         run_context: ContextWrapper[TContext],
         tool_executor: BaseFunctionToolExecutor[TContext],
         agent_hooks: BaseAgentRunHooks[TContext],
+        streaming: bool = False,
+        # enforce max turns, will discard older turns when exceeded BEFORE compression
+        # -1 means no limit
+        enforce_max_turns: int = -1,
+        # llm compressor
+        llm_compress_instruction: str | None = None,
+        llm_compress_keep_recent: int = 0,
+        llm_compress_provider: Provider | None = None,
+        # truncate by turns compressor
+        truncate_turns: int = 1,
+        # customize
+        custom_token_counter: TokenCounter | None = None,
+        custom_compressor: ContextCompressor | None = None,
         **kwargs: T.Any,
     ) -> None:
         self.req = request
-        self.streaming = kwargs.get("streaming", False)
+        self.streaming = streaming
+        self.enforce_max_turns = enforce_max_turns
+        self.llm_compress_instruction = llm_compress_instruction
+        self.llm_compress_keep_recent = llm_compress_keep_recent
+        self.llm_compress_provider = llm_compress_provider
+        self.truncate_turns = truncate_turns
+        self.custom_token_counter = custom_token_counter
+        self.custom_compressor = custom_compressor
+        # we will do compress when:
+        # 1. before requesting LLM
+        # TODO: 2. after LLM output a tool call
+        self.context_config = ContextConfig(
+            # <=0 will never do compress
+            max_context_tokens=provider.provider_config.get("max_context_tokens", 0),
+            # enforce max turns before compression
+            enforce_max_turns=self.enforce_max_turns,
+            truncate_turns=self.truncate_turns,
+            llm_compress_instruction=self.llm_compress_instruction,
+            llm_compress_keep_recent=self.llm_compress_keep_recent,
+            llm_compress_provider=self.llm_compress_provider,
+            custom_token_counter=self.custom_token_counter,
+            custom_compressor=self.custom_compressor,
+        )
+        self.context_manager = ContextManager(self.context_config)
+
         self.provider = provider
         self.final_llm_resp = None
         self._state = AgentState.IDLE
@@ -110,6 +151,12 @@ class ToolLoopAgentRunner(BaseAgentRunner[TContext]):
         self._transition_state(AgentState.RUNNING)
         llm_resp_result = None
 
+        # do truncate and compress
+        token_usage = self.req.conversation.token_usage if self.req.conversation else 0
+        self.run_context.messages = await self.context_manager.process(
+            self.run_context.messages, trusted_token_usage=token_usage
+        )
+
         async for llm_response in self._iter_llm_responses():
             if llm_response.is_chunk:
                 # update ttft

astrbot/core/config/default.py

@@ -5,7 +5,7 @@ from typing import Any, TypedDict
 
 from astrbot.core.utils.astrbot_path import get_astrbot_data_path
 
-VERSION = "4.10.5"
+VERSION = "4.11.0"
 DB_PATH = os.path.join(get_astrbot_data_path(), "data_v4.db")
 
 WEBHOOK_SUPPORTED_PLATFORMS = [
@@ -83,6 +83,16 @@ DEFAULT_CONFIG = {
         "default_personality": "default",
         "persona_pool": ["*"],
         "prompt_prefix": "{{prompt}}",
+        "context_limit_reached_strategy": "truncate_by_turns",  # or llm_compress
+        "llm_compress_instruction": (
+            "Based on our full conversation history, produce a concise summary of key takeaways and/or project progress.\n"
+            "1. Systematically cover all core topics discussed and the final conclusion/outcome for each; clearly highlight the latest primary focus.\n"
+            "2. If any tools were used, summarize tool usage (total call count) and extract the most valuable insights from tool outputs.\n"
+            "3. If there was an initial user goal, state it first and describe the current progress/status.\n"
+            "4. Write the summary in the user's language.\n"
+        ),
+        "llm_compress_keep_recent": 4,
+        "llm_compress_provider_id": "",
         "max_context_length": -1,
         "dequeue_context_length": 1,
         "streaming_response": False,
@@ -179,6 +189,7 @@ class ChatProviderTemplate(TypedDict):
     model: str
     modalities: list
     custom_extra_body: dict[str, Any]
+    max_context_tokens: int
 
 
 CHAT_PROVIDER_TEMPLATE = {
@@ -187,6 +198,7 @@ CHAT_PROVIDER_TEMPLATE = {
     "model": "",
     "modalities": [],
     "custom_extra_body": {},
+    "max_context_tokens": 0,
 }
 
 """
@@ -227,7 +239,7 @@ CONFIG_METADATA_2 = {
                         "callback_server_host": "0.0.0.0",
                         "port": 6196,
                     },
-                    "OneBot v11": {
+                    "OneBot v11 (QQ 个人号等)": {
                         "id": "default",
                         "type": "aiocqhttp",
                         "enable": False,
@@ -235,16 +247,6 @@ CONFIG_METADATA_2 = {
                         "ws_reverse_port": 6199,
                         "ws_reverse_token": "",
                     },
-                    "WeChatPadPro": {
-                        "id": "wechatpadpro",
-                        "type": "wechatpadpro",
-                        "enable": False,
-                        "admin_key": "stay33",
-                        "host": "这里填写你的局域网IP或者公网服务器IP",
-                        "port": 8059,
-                        "wpp_active_message_poll": False,
-                        "wpp_active_message_poll_interval": 3,
-                    },
                     "微信公众平台": {
                         "id": "weixin_official_account",
                         "type": "weixin_official_account",
@@ -374,6 +376,16 @@ CONFIG_METADATA_2 = {
                         "satori_heartbeat_interval": 10,
                         "satori_reconnect_delay": 5,
                     },
+                    "WeChatPadPro": {
+                        "id": "wechatpadpro",
+                        "type": "wechatpadpro",
+                        "enable": False,
+                        "admin_key": "stay33",
+                        "host": "这里填写你的局域网IP或者公网服务器IP",
+                        "port": 8059,
+                        "wpp_active_message_poll": False,
+                        "wpp_active_message_poll_interval": 3,
+                    },
                     # "WebChat": {
                     #     "id": "webchat",
                     #     "type": "webchat",
@@ -2033,6 +2045,11 @@ CONFIG_METADATA_2 = {
                         "type": "string",
                         "hint": "模型名称，如 gpt-4o-mini, deepseek-chat。",
                     },
+                    "max_context_tokens": {
+                        "description": "模型上下文窗口大小",
+                        "type": "int",
+                        "hint": "模型最大上下文 Token 大小。如果为 0，则会自动从模型元数据填充（如有），也可手动修改。",
+                    },
                     "dify_api_key": {
                         "description": "API Key",
                         "type": "string",
@@ -2540,6 +2557,66 @@ CONFIG_METADATA_3 = {
             #         "provider_settings.enable": True,
             #     },
             # },
+            "truncate_and_compress": {
+                "description": "上下文管理策略",
+                "type": "object",
+                "items": {
+                    "provider_settings.max_context_length": {
+                        "description": "最多携带对话轮数",
+                        "type": "int",
+                        "hint": "超出这个数量时丢弃最旧的部分，一轮聊天记为 1 条，-1 为不限制",
+                        "condition": {
+                            "provider_settings.agent_runner_type": "local",
+                        },
+                    },
+                    "provider_settings.dequeue_context_length": {
+                        "description": "丢弃对话轮数",
+                        "type": "int",
+                        "hint": "超出最多携带对话轮数时, 一次丢弃的聊天轮数",
+                        "condition": {
+                            "provider_settings.agent_runner_type": "local",
+                        },
+                    },
+                    "provider_settings.context_limit_reached_strategy": {
+                        "description": "超出模型上下文窗口时的处理方式",
+                        "type": "string",
+                        "options": ["truncate_by_turns", "llm_compress"],
+                        "labels": ["按对话轮数截断", "由 LLM 压缩上下文"],
+                        "condition": {
+                            "provider_settings.agent_runner_type": "local",
+                        },
+                        "hint": "",
+                    },
+                    "provider_settings.llm_compress_instruction": {
+                        "description": "上下文压缩提示词",
+                        "type": "text",
+                        "hint": "如果为空则使用默认提示词。",
+                        "condition": {
+                            "provider_settings.context_limit_reached_strategy": "llm_compress",
+                            "provider_settings.agent_runner_type": "local",
+                        },
+                    },
+                    "provider_settings.llm_compress_keep_recent": {
+                        "description": "压缩时保留最近对话轮数",
+                        "type": "int",
+                        "hint": "始终保留的最近 N 轮对话。",
+                        "condition": {
+                            "provider_settings.context_limit_reached_strategy": "llm_compress",
+                            "provider_settings.agent_runner_type": "local",
+                        },
+                    },
+                    "provider_settings.llm_compress_provider_id": {
+                        "description": "用于上下文压缩的模型提供商 ID",
+                        "type": "string",
+                        "_special": "select_provider",
+                        "hint": "留空时将降级为“按对话轮数截断”的策略。",
+                        "condition": {
+                            "provider_settings.context_limit_reached_strategy": "llm_compress",
+                            "provider_settings.agent_runner_type": "local",
+                        },
+                    },
+                },
+            },
             "others": {
                 "description": "其他配置",
                 "type": "object",
@@ -2604,22 +2681,6 @@ CONFIG_METADATA_3 = {
                             "provider_settings.streaming_response": True,
                         },
                     },
-                    "provider_settings.max_context_length": {
-                        "description": "最多携带对话轮数",
-                        "type": "int",
-                        "hint": "超出这个数量时丢弃最旧的部分，一轮聊天记为 1 条，-1 为不限制",
-                        "condition": {
-                            "provider_settings.agent_runner_type": "local",
-                        },
-                    },
-                    "provider_settings.dequeue_context_length": {
-                        "description": "丢弃对话轮数",
-                        "type": "int",
-                        "hint": "超出最多携带对话轮数时, 一次丢弃的聊天轮数",
-                        "condition": {
-                            "provider_settings.agent_runner_type": "local",
-                        },
-                    },
                     "provider_settings.wake_prefix": {
                         "description": "LLM 聊天额外唤醒前缀 ",
                         "type": "string",

astrbot/core/conversation_mgr.py

@@ -69,6 +69,7 @@ class ConversationManager:
             persona_id=conv_v2.persona_id,
             created_at=created_at,
             updated_at=updated_at,
+            token_usage=conv_v2.token_usage,
         )
 
     async def new_conversation(
@@ -256,6 +257,7 @@ class ConversationManager:
         history: list[dict] | None = None,
         title: str | None = None,
         persona_id: str | None = None,
+        token_usage: int | None = None,
     ) -> None:
         """更新会话的对话.
 
@@ -263,6 +265,7 @@ class ConversationManager:
             unified_msg_origin (str): 统一的消息来源字符串。格式为 platform_name:message_type:session_id
             conversation_id (str): 对话 ID, 是 uuid 格式的字符串
             history (List[Dict]): 对话历史记录, 是一个字典列表, 每个字典包含 role 和 content 字段
+            token_usage (int | None): token 使用量。None 表示不更新
 
         """
         if not conversation_id:
@@ -274,6 +277,7 @@ class ConversationManager:
                 title=title,
                 persona_id=persona_id,
                 content=history,
+                token_usage=token_usage,
             )
 
     async def update_conversation_title(

astrbot/core/core_lifecycle.py

@@ -90,6 +90,7 @@ class AstrBotCoreLifecycle:
 
         # 初始化 UMOP 配置路由器
         self.umop_config_router = UmopConfigRouter(sp=sp)
+        await self.umop_config_router.initialize()
 
         # 初始化 AstrBot 配置管理器
         self.astrbot_config_mgr = AstrBotConfigManager(

astrbot/core/db/__init__.py

@@ -152,6 +152,7 @@ class BaseDatabase(abc.ABC):
         title: str | None = None,
         persona_id: str | None = None,
         content: list[dict] | None = None,
+        token_usage: int | None = None,
     ) -> None:
         """Update a conversation's history."""
         ...

astrbot/core/db/migration/migra_token_usage.py

@@ -0,0 +1,61 @@
+"""Migration script to add token_usage column to conversations table.
+
+This migration adds the token_usage field to track token consumption for each conversation.
+
+Changes:
+- Adds token_usage column to conversations table (default: 0)
+"""
+
+from sqlalchemy import text
+
+from astrbot.api import logger, sp
+from astrbot.core.db import BaseDatabase
+
+
+async def migrate_token_usage(db_helper: BaseDatabase):
+    """Add token_usage column to conversations table.
+
+    This migration adds a new column to track token consumption in conversations.
+    """
+    # 检查是否已经完成迁移
+    migration_done = await db_helper.get_preference(
+        "global", "global", "migration_done_token_usage_1"
+    )
+    if migration_done:
+        return
+
+    logger.info("开始执行数据库迁移（添加 conversations.token_usage 列）...")
+
+    # 这里只适配了 SQLite。因为截止至这一版本，AstrBot 仅支持 SQLite。
+
+    try:
+        async with db_helper.get_db() as session:
+            # 检查列是否已存在
+            result = await session.execute(text("PRAGMA table_info(conversations)"))
+            columns = result.fetchall()
+            column_names = [col[1] for col in columns]
+
+            if "token_usage" in column_names:
+                logger.info("token_usage 列已存在，跳过迁移")
+                await sp.put_async(
+                    "global", "global", "migration_done_token_usage_1", True
+                )
+                return
+
+            # 添加 token_usage 列
+            await session.execute(
+                text(
+                    "ALTER TABLE conversations ADD COLUMN token_usage INTEGER NOT NULL DEFAULT 0"
+                )
+            )
+            await session.commit()
+
+            logger.info("token_usage 列添加成功")
+
+        # 标记迁移完成
+        await sp.put_async("global", "global", "migration_done_token_usage_1", True)
+        logger.info("token_usage 迁移完成")
+
+    except Exception as e:
+        logger.error(f"迁移过程中发生错误: {e}", exc_info=True)
+        raise

astrbot/core/db/po.py

@@ -54,6 +54,11 @@ class ConversationV2(SQLModel, table=True):
     )
     title: str | None = Field(default=None, max_length=255)
     persona_id: str | None = Field(default=None)
+    token_usage: int = Field(default=0, nullable=False)
+    """content is a list of OpenAI-formated messages in list[dict] format.
+    token_usage is the total token value of the messages.
+    when 0, will use estimated token counter.
+    """
 
     __table_args__ = (
         UniqueConstraint(
@@ -313,6 +318,8 @@ class Conversation:
     persona_id: str | None = ""
     created_at: int = 0
     updated_at: int = 0
+    token_usage: int = 0
+    """对话的总 token 数量。AstrBot 会保留最近一次 LLM 请求返回的总 token 数，方便统计。token_usage 可能为 0，表示未知。"""
 
 
 class Personality(TypedDict):

astrbot/core/db/sqlite.py

@@ -241,7 +241,9 @@ class SQLiteDatabase(BaseDatabase):
                 session.add(new_conversation)
                 return new_conversation
 
-    async def update_conversation(self, cid, title=None, persona_id=None, content=None):
+    async def update_conversation(
+        self, cid, title=None, persona_id=None, content=None, token_usage=None
+    ):
         async with self.get_db() as session:
             session: AsyncSession
             async with session.begin():
@@ -255,6 +257,8 @@ class SQLiteDatabase(BaseDatabase):
                     values["persona_id"] = persona_id
                 if content is not None:
                     values["content"] = content
+                if token_usage is not None:
+                    values["token_usage"] = token_usage
                 if not values:
                     return None
                 query = query.values(**values)

astrbot/core/pipeline/process_stage/method/agent_request.py

@@ -38,7 +38,7 @@ class AgentRequestSubStage(Stage):
             )
             return
 
-        if not SessionServiceManager.should_process_llm_request(event):
+        if not await SessionServiceManager.should_process_llm_request(event):
             logger.debug(
                 f"The session {event.unified_msg_origin} has disabled AI capability, skipping processing."
             )

astrbot/core/pipeline/process_stage/method/agent_sub_stages/internal.py

@@ -1,12 +1,12 @@
 """本地 Agent 模式的 LLM 调用 Stage"""
 
 import asyncio
-import copy
 import json
 from collections.abc import AsyncGenerator
 
 from astrbot.core import logger
 from astrbot.core.agent.message import Message
+from astrbot.core.agent.response import AgentStats
 from astrbot.core.agent.tool import ToolSet
 from astrbot.core.astr_agent_context import AstrAgentContext
 from astrbot.core.conversation_mgr import Conversation
@@ -24,6 +24,7 @@ from astrbot.core.provider.entities import (
 )
 from astrbot.core.star.star_handler import EventType, star_map
 from astrbot.core.utils.file_extract import extract_file_moonshotai
+from astrbot.core.utils.llm_metadata import LLM_METADATAS
 from astrbot.core.utils.metrics import Metric
 from astrbot.core.utils.session_lock import session_lock_manager
 
@@ -41,11 +42,6 @@ class InternalAgentSubStage(Stage):
         self.ctx = ctx
         conf = ctx.astrbot_config
         settings = conf["provider_settings"]
-        self.max_context_length = settings["max_context_length"]  # int
-        self.dequeue_context_length: int = min(
-            max(1, settings["dequeue_context_length"]),
-            self.max_context_length - 1,
-        )
         self.streaming_response: bool = settings["streaming_response"]
         self.unsupported_streaming_strategy: str = settings[
             "unsupported_streaming_strategy"
@@ -65,6 +61,25 @@ class InternalAgentSubStage(Stage):
             "moonshotai_api_key", ""
         )
 
+        # 上下文管理相关
+        self.context_limit_reached_strategy: str = settings.get(
+            "context_limit_reached_strategy", "truncate_by_turns"
+        )
+        self.llm_compress_instruction: str = settings.get(
+            "llm_compress_instruction", ""
+        )
+        self.llm_compress_keep_recent: int = settings.get("llm_compress_keep_recent", 4)
+        self.llm_compress_provider_id: str = settings.get(
+            "llm_compress_provider_id", ""
+        )
+        self.max_context_length = settings["max_context_length"]  # int
+        self.dequeue_context_length: int = min(
+            max(1, settings["dequeue_context_length"]),
+            self.max_context_length - 1,
+        )
+        if self.dequeue_context_length <= 0:
+            self.dequeue_context_length = 1
+
         self.conv_manager = ctx.plugin_manager.context.conversation_manager
 
     def _select_provider(self, event: AstrMessageEvent):
@@ -167,34 +182,6 @@ class InternalAgentSubStage(Stage):
                 },
             )
 
-    def _truncate_contexts(
-        self,
-        contexts: list[dict],
-    ) -> list[dict]:
-        """截断上下文列表，确保不超过最大长度"""
-        if self.max_context_length == -1:
-            return contexts
-
-        if len(contexts) // 2 <= self.max_context_length:
-            return contexts
-
-        truncated_contexts = contexts[
-            -(self.max_context_length - self.dequeue_context_length + 1) * 2 :
-        ]
-        # 找到第一个role 为 user 的索引，确保上下文格式正确
-        index = next(
-            (
-                i
-                for i, item in enumerate(truncated_contexts)
-                if item.get("role") == "user"
-            ),
-            None,
-        )
-        if index is not None and index > 0:
-            truncated_contexts = truncated_contexts[index:]
-
-        return truncated_contexts
-
     def _modalities_fix(
         self,
         provider: Provider,
@@ -296,6 +283,7 @@ class InternalAgentSubStage(Stage):
         req: ProviderRequest,
         llm_response: LLMResponse | None,
         all_messages: list[Message],
+        runner_stats: AgentStats | None,
     ):
         if (
             not req
@@ -322,27 +310,37 @@ class InternalAgentSubStage(Stage):
                 continue
             message_to_save.append(message.model_dump())
 
+        # get token usage from agent runner stats
+        token_usage = None
+        if runner_stats:
+            token_usage = runner_stats.token_usage.total
+
         await self.conv_manager.update_conversation(
             event.unified_msg_origin,
             req.conversation.cid,
             history=message_to_save,
+            token_usage=token_usage,
         )
 
-    def _fix_messages(self, messages: list[dict]) -> list[dict]:
-        """验证并且修复上下文"""
-        fixed_messages = []
-        for message in messages:
-            if message.get("role") == "tool":
-                # tool block 前面必须要有 user 和 assistant block
-                if len(fixed_messages) < 2:
-                    # 这种情况可能是上下文被截断导致的
-                    # 我们直接将之前的上下文都清空
-                    fixed_messages = []
-                else:
-                    fixed_messages.append(message)
-            else:
-                fixed_messages.append(message)
-        return fixed_messages
+    def _get_compress_provider(self) -> Provider | None:
+        if not self.llm_compress_provider_id:
+            return None
+        if self.context_limit_reached_strategy != "llm_compress":
+            return None
+        provider = self.ctx.plugin_manager.context.get_provider_by_id(
+            self.llm_compress_provider_id,
+        )
+        if provider is None:
+            logger.warning(
+                f"未找到指定的上下文压缩模型 {self.llm_compress_provider_id}，将跳过压缩。",
+            )
+            return None
+        if not isinstance(provider, Provider):
+            logger.warning(
+                f"指定的上下文压缩模型 {self.llm_compress_provider_id} 不是对话模型，将跳过压缩。"
+            )
+            return None
+        return provider
 
     async def process(
         self, event: AstrMessageEvent, provider_wake_prefix: str
@@ -364,6 +362,10 @@ class InternalAgentSubStage(Stage):
                 streaming_response = bool(enable_streaming)
 
             logger.debug("ready to request llm provider")
+
+            # 通知等待调用 LLM（在获取锁之前）
+            await call_event_hook(event, EventType.OnWaitingLLMRequestEvent)
+
             async with session_lock_manager.acquire_lock(event.unified_msg_origin):
                 logger.debug("acquired session lock for llm request")
                 if event.get_extra("provider_request"):
@@ -422,9 +424,10 @@ class InternalAgentSubStage(Stage):
                 await self._apply_kb(event, req)
 
                 # truncate contexts to fit max length
-                if req.contexts:
-                    req.contexts = self._truncate_contexts(req.contexts)
-                    self._fix_messages(req.contexts)
+                # NOW moved to ContextManager inside ToolLoopAgentRunner
+                # if req.contexts:
+                #     req.contexts = self._truncate_contexts(req.contexts)
+                #     self._fix_messages(req.contexts)
 
                 # session_id
                 if not req.session_id:
@@ -440,8 +443,6 @@ class InternalAgentSubStage(Stage):
                     self.unsupported_streaming_strategy == "turn_off"
                     and not event.platform_meta.support_streaming_message
                 )
-                # 备份 req.contexts
-                backup_contexts = copy.deepcopy(req.contexts)
 
                 # run agent
                 agent_runner = AgentRunner()
@@ -452,6 +453,15 @@ class InternalAgentSubStage(Stage):
                     context=self.ctx.plugin_manager.context,
                     event=event,
                 )
+
+                # inject model context length limit
+                if provider.provider_config.get("max_context_tokens", 0) <= 0:
+                    model = provider.get_model()
+                    if model_info := LLM_METADATAS.get(model):
+                        provider.provider_config["max_context_tokens"] = model_info[
+                            "limit"
+                        ]["context"]
+
                 await agent_runner.reset(
                     provider=provider,
                     request=req,
@@ -462,6 +472,11 @@ class InternalAgentSubStage(Stage):
                     tool_executor=FunctionToolExecutor(),
                     agent_hooks=MAIN_AGENT_HOOKS,
                     streaming=streaming_response,
+                    llm_compress_instruction=self.llm_compress_instruction,
+                    llm_compress_keep_recent=self.llm_compress_keep_recent,
+                    llm_compress_provider=self._get_compress_provider(),
+                    truncate_turns=self.dequeue_context_length,
+                    enforce_max_turns=self.max_context_length,
                 )
 
                 if streaming_response and not stream_to_general:
@@ -507,14 +522,12 @@ class InternalAgentSubStage(Stage):
                     ):
                         yield
 
-                # 恢复备份的 contexts
-                req.contexts = backup_contexts
-
                 await self._save_to_history(
                     event,
                     req,
                     agent_runner.get_final_llm_resp(),
                     agent_runner.run_context.messages,
+                    agent_runner.stats,
                 )
 
             # 异步处理 WebChat 特殊情况

astrbot/core/pipeline/result_decorate/stage.py

@@ -260,7 +260,7 @@ class ResultDecorateStage(Stage):
             should_tts = (
                 bool(self.ctx.astrbot_config["provider_tts_settings"]["enable"])
                 and result.is_llm_result()
-                and SessionServiceManager.should_process_tts_request(event)
+                and await SessionServiceManager.should_process_tts_request(event)
                 and random.random() <= self.tts_trigger_probability
                 and tts_provider
             )

astrbot/core/pipeline/session_status_check/stage.py

@@ -21,7 +21,7 @@ class SessionStatusCheckStage(Stage):
         event: AstrMessageEvent,
     ) -> None | AsyncGenerator[None, None]:
         # 检查会话是否整体启用
-        if not SessionServiceManager.is_session_enabled(event.unified_msg_origin):
+        if not await SessionServiceManager.is_session_enabled(event.unified_msg_origin):
             logger.debug(f"会话 {event.unified_msg_origin} 已被关闭，已终止事件传播。")
 
             # workaround for #2309