AstrBot 4.12.3__py3-none-any.whl → 4.13.0__py3-none-any.whl

astrbot/core/astr_agent_run_util.py

@@ -1,3 +1,6 @@
+import asyncio
+import re
+import time
 import traceback
 from collections.abc import AsyncGenerator
 
@@ -5,13 +8,14 @@ from astrbot.core import logger
 from astrbot.core.agent.message import Message
 from astrbot.core.agent.runners.tool_loop_agent_runner import ToolLoopAgentRunner
 from astrbot.core.astr_agent_context import AstrAgentContext
-from astrbot.core.message.components import Json
+from astrbot.core.message.components import BaseMessageComponent, Json, Plain
 from astrbot.core.message.message_event_result import (
     MessageChain,
     MessageEventResult,
     ResultContentType,
 )
 from astrbot.core.provider.entities import LLMResponse
+from astrbot.core.provider.provider import TTSProvider
 
 AgentRunner = ToolLoopAgentRunner[AstrAgentContext]
 
@@ -131,3 +135,241 @@ async def run_agent(
             else:
                 astr_event.set_result(MessageEventResult().message(err_msg))
             return
+
+
+async def run_live_agent(
+    agent_runner: AgentRunner,
+    tts_provider: TTSProvider | None = None,
+    max_step: int = 30,
+    show_tool_use: bool = True,
+    show_reasoning: bool = False,
+) -> AsyncGenerator[MessageChain | None, None]:
+    """Live Mode 的 Agent 运行器，支持流式 TTS
+
+    Args:
+        agent_runner: Agent 运行器
+        tts_provider: TTS Provider 实例
+        max_step: 最大步数
+        show_tool_use: 是否显示工具使用
+        show_reasoning: 是否显示推理过程
+
+    Yields:
+        MessageChain: 包含文本或音频数据的消息链
+    """
+    # 如果没有 TTS Provider，直接发送文本
+    if not tts_provider:
+        async for chain in run_agent(
+            agent_runner,
+            max_step=max_step,
+            show_tool_use=show_tool_use,
+            stream_to_general=False,
+            show_reasoning=show_reasoning,
+        ):
+            yield chain
+        return
+
+    support_stream = tts_provider.support_stream()
+    if support_stream:
+        logger.info("[Live Agent] 使用流式 TTS（原生支持 get_audio_stream）")
+    else:
+        logger.info(
+            f"[Live Agent] 使用 TTS（{tts_provider.meta().type} "
+            "使用 get_audio，将按句子分块生成音频）"
+        )
+
+    # 统计数据初始化
+    tts_start_time = time.time()
+    tts_first_frame_time = 0.0
+    first_chunk_received = False
+
+    # 创建队列
+    text_queue: asyncio.Queue[str | None] = asyncio.Queue()
+    # audio_queue stored bytes or (text, bytes)
+    audio_queue: asyncio.Queue[bytes | tuple[str, bytes] | None] = asyncio.Queue()
+
+    # 1. 启动 Agent Feeder 任务：负责运行 Agent 并将文本分句喂给 text_queue
+    feeder_task = asyncio.create_task(
+        _run_agent_feeder(
+            agent_runner, text_queue, max_step, show_tool_use, show_reasoning
+        )
+    )
+
+    # 2. 启动 TTS 任务：负责从 text_queue 读取文本并生成音频到 audio_queue
+    if support_stream:
+        tts_task = asyncio.create_task(
+            _safe_tts_stream_wrapper(tts_provider, text_queue, audio_queue)
+        )
+    else:
+        tts_task = asyncio.create_task(
+            _simulated_stream_tts(tts_provider, text_queue, audio_queue)
+        )
+
+    # 3. 主循环：从 audio_queue 读取音频并 yield
+    try:
+        while True:
+            queue_item = await audio_queue.get()
+
+            if queue_item is None:
+                break
+
+            text = None
+            if isinstance(queue_item, tuple):
+                text, audio_data = queue_item
+            else:
+                audio_data = queue_item
+
+            if not first_chunk_received:
+                # 记录首帧延迟（从开始处理到收到第一个音频块）
+                tts_first_frame_time = time.time() - tts_start_time
+                first_chunk_received = True
+
+            # 将音频数据封装为 MessageChain
+            import base64
+
+            audio_b64 = base64.b64encode(audio_data).decode("utf-8")
+            comps: list[BaseMessageComponent] = [Plain(audio_b64)]
+            if text:
+                comps.append(Json(data={"text": text}))
+            chain = MessageChain(chain=comps, type="audio_chunk")
+            yield chain
+
+    except Exception as e:
+        logger.error(f"[Live Agent] 运行时发生错误: {e}", exc_info=True)
+    finally:
+        # 清理任务
+        if not feeder_task.done():
+            feeder_task.cancel()
+        if not tts_task.done():
+            tts_task.cancel()
+
+        # 确保队列被消费
+        pass
+
+    tts_end_time = time.time()
+
+    # 发送 TTS 统计信息
+    try:
+        astr_event = agent_runner.run_context.context.event
+        if astr_event.get_platform_name() == "webchat":
+            tts_duration = tts_end_time - tts_start_time
+            await astr_event.send(
+                MessageChain(
+                    type="tts_stats",
+                    chain=[
+                        Json(
+                            data={
+                                "tts_total_time": tts_duration,
+                                "tts_first_frame_time": tts_first_frame_time,
+                                "tts": tts_provider.meta().type,
+                                "chat_model": agent_runner.provider.get_model(),
+                            }
+                        )
+                    ],
+                )
+            )
+    except Exception as e:
+        logger.error(f"发送 TTS 统计信息失败: {e}")
+
+
+async def _run_agent_feeder(
+    agent_runner: AgentRunner,
+    text_queue: asyncio.Queue,
+    max_step: int,
+    show_tool_use: bool,
+    show_reasoning: bool,
+):
+    """运行 Agent 并将文本输出分句放入队列"""
+    buffer = ""
+    try:
+        async for chain in run_agent(
+            agent_runner,
+            max_step=max_step,
+            show_tool_use=show_tool_use,
+            stream_to_general=False,
+            show_reasoning=show_reasoning,
+        ):
+            if chain is None:
+                continue
+
+            # 提取文本
+            text = chain.get_plain_text()
+            if text:
+                buffer += text
+
+                # 分句逻辑：匹配标点符号
+                # r"([.。!！?？\n]+)" 会保留分隔符
+                parts = re.split(r"([.。!！?？\n]+)", buffer)
+
+                if len(parts) > 1:
+                    # 处理完整的句子
+                    # range step 2 因为 split 后是 [text, delim, text, delim, ...]
+                    temp_buffer = ""
+                    for i in range(0, len(parts) - 1, 2):
+                        sentence = parts[i]
+                        delim = parts[i + 1]
+                        full_sentence = sentence + delim
+                        temp_buffer += full_sentence
+
+                        if len(temp_buffer) >= 10:
+                            if temp_buffer.strip():
+                                logger.info(f"[Live Agent Feeder] 分句: {temp_buffer}")
+                                await text_queue.put(temp_buffer)
+                            temp_buffer = ""
+
+                    # 更新 buffer 为剩余部分
+                    buffer = temp_buffer + parts[-1]
+
+        # 处理剩余 buffer
+        if buffer.strip():
+            await text_queue.put(buffer)
+
+    except Exception as e:
+        logger.error(f"[Live Agent Feeder] Error: {e}", exc_info=True)
+    finally:
+        # 发送结束信号
+        await text_queue.put(None)
+
+
+async def _safe_tts_stream_wrapper(
+    tts_provider: TTSProvider,
+    text_queue: asyncio.Queue[str | None],
+    audio_queue: "asyncio.Queue[bytes | tuple[str, bytes] | None]",
+):
+    """包装原生流式 TTS 确保异常处理和队列关闭"""
+    try:
+        await tts_provider.get_audio_stream(text_queue, audio_queue)
+    except Exception as e:
+        logger.error(f"[Live TTS Stream] Error: {e}", exc_info=True)
+    finally:
+        await audio_queue.put(None)
+
+
+async def _simulated_stream_tts(
+    tts_provider: TTSProvider,
+    text_queue: asyncio.Queue[str | None],
+    audio_queue: "asyncio.Queue[bytes | tuple[str, bytes] | None]",
+):
+    """模拟流式 TTS 分句生成音频"""
+    try:
+        while True:
+            text = await text_queue.get()
+            if text is None:
+                break
+
+            try:
+                audio_path = await tts_provider.get_audio(text)
+
+                if audio_path:
+                    with open(audio_path, "rb") as f:
+                        audio_data = f.read()
+                    await audio_queue.put((text, audio_data))
+            except Exception as e:
+                logger.error(
+                    f"[Live TTS Simulated] Error processing text '{text[:20]}...': {e}"
+                )
+                # 继续处理下一句
+
+    except Exception as e:
+        logger.error(f"[Live TTS Simulated] Critical Error: {e}", exc_info=True)
+    finally:
+        await audio_queue.put(None)

astrbot/core/astr_agent_tool_exec.py

@@ -256,7 +256,7 @@ async def call_local_llm_tool(
                 # 这里逐步执行异步生成器, 对于每个 yield 返回的 ret, 执行下面的代码
                 # 返回值只能是 MessageEventResult 或者 None（无返回值）
                 _has_yielded = True
-                if isinstance(ret, (MessageEventResult, CommandResult)):
+                if isinstance(ret, MessageEventResult | CommandResult):
                     # 如果返回值是 MessageEventResult, 设置结果并继续
                     event.set_result(ret)
                     yield
@@ -273,7 +273,7 @@ async def call_local_llm_tool(
     elif inspect.iscoroutine(ready_to_call):
         # 如果只是一个协程, 直接执行
         ret = await ready_to_call
-        if isinstance(ret, (MessageEventResult, CommandResult)):
+        if isinstance(ret, MessageEventResult | CommandResult):
             event.set_result(ret)
             yield
         else:

astrbot/core/{sandbox → computer}/booters/base.py

@@ -1,7 +1,7 @@
 from ..olayer import FileSystemComponent, PythonComponent, ShellComponent
 
 
-class SandboxBooter:
+class ComputerBooter:
     @property
     def fs(self) -> FileSystemComponent: ...
 
@@ -16,16 +16,16 @@ class SandboxBooter:
     async def shutdown(self) -> None: ...
 
     async def upload_file(self, path: str, file_name: str) -> dict:
-        """Upload file to sandbox.
+        """Upload file to the computer.
 
         Should return a dict with `success` (bool) and `file_path` (str) keys.
         """
         ...
 
     async def download_file(self, remote_path: str, local_path: str):
-        """Download file from sandbox."""
+        """Download file from the computer."""
         ...
 
     async def available(self) -> bool:
-        """Check if the sandbox is available."""
+        """Check if the computer is available."""
         ...

astrbot/core/{sandbox → computer}/booters/boxlite.py

@@ -11,7 +11,7 @@ from shipyard.shell import ShellComponent as ShipyardShellComponent
 from astrbot.api import logger
 
 from ..olayer import FileSystemComponent, PythonComponent, ShellComponent
-from .base import SandboxBooter
+from .base import ComputerBooter
 
 
 class MockShipyardSandboxClient:
@@ -124,7 +124,7 @@ class MockShipyardSandboxClient:
                 loop -= 1
 
 
-class BoxliteBooter(SandboxBooter):
+class BoxliteBooter(ComputerBooter):
     async def boot(self, session_id: str) -> None:
         logger.info(
             f"Booting(Boxlite) for session: {session_id}, this may take a while..."

astrbot/core/computer/booters/local.py

@@ -0,0 +1,234 @@
+from __future__ import annotations
+
+import asyncio
+import os
+import shutil
+import subprocess
+import sys
+from dataclasses import dataclass
+from typing import Any
+
+from astrbot.api import logger
+from astrbot.core.utils.astrbot_path import (
+    get_astrbot_data_path,
+    get_astrbot_root,
+    get_astrbot_temp_path,
+)
+
+from ..olayer import FileSystemComponent, PythonComponent, ShellComponent
+from .base import ComputerBooter
+
+_BLOCKED_COMMAND_PATTERNS = [
+    " rm -rf ",
+    " rm -fr ",
+    " rm -r ",
+    " mkfs",
+    " dd if=",
+    " shutdown",
+    " reboot",
+    " poweroff",
+    " halt",
+    " sudo ",
+    ":(){:|:&};:",
+    " kill -9 ",
+    " killall ",
+]
+
+
+def _is_safe_command(command: str) -> bool:
+    cmd = f" {command.strip().lower()} "
+    return not any(pat in cmd for pat in _BLOCKED_COMMAND_PATTERNS)
+
+
+def _ensure_safe_path(path: str) -> str:
+    abs_path = os.path.abspath(path)
+    allowed_roots = [
+        os.path.abspath(get_astrbot_root()),
+        os.path.abspath(get_astrbot_data_path()),
+        os.path.abspath(get_astrbot_temp_path()),
+    ]
+    if not any(abs_path.startswith(root) for root in allowed_roots):
+        raise PermissionError("Path is outside the allowed computer roots.")
+    return abs_path
+
+
+@dataclass
+class LocalShellComponent(ShellComponent):
+    async def exec(
+        self,
+        command: str,
+        cwd: str | None = None,
+        env: dict[str, str] | None = None,
+        timeout: int | None = 30,
+        shell: bool = True,
+        background: bool = False,
+    ) -> dict[str, Any]:
+        if not _is_safe_command(command):
+            raise PermissionError("Blocked unsafe shell command.")
+
+        def _run() -> dict[str, Any]:
+            run_env = os.environ.copy()
+            if env:
+                run_env.update({str(k): str(v) for k, v in env.items()})
+            working_dir = _ensure_safe_path(cwd) if cwd else get_astrbot_root()
+            if background:
+                proc = subprocess.Popen(
+                    command,
+                    shell=shell,
+                    cwd=working_dir,
+                    env=run_env,
+                    stdout=subprocess.PIPE,
+                    stderr=subprocess.PIPE,
+                    text=True,
+                )
+                return {"pid": proc.pid, "stdout": "", "stderr": "", "exit_code": None}
+            result = subprocess.run(
+                command,
+                shell=shell,
+                cwd=working_dir,
+                env=run_env,
+                timeout=timeout,
+                capture_output=True,
+                text=True,
+            )
+            return {
+                "stdout": result.stdout,
+                "stderr": result.stderr,
+                "exit_code": result.returncode,
+            }
+
+        return await asyncio.to_thread(_run)
+
+
+@dataclass
+class LocalPythonComponent(PythonComponent):
+    async def exec(
+        self,
+        code: str,
+        kernel_id: str | None = None,
+        timeout: int = 30,
+        silent: bool = False,
+    ) -> dict[str, Any]:
+        def _run() -> dict[str, Any]:
+            try:
+                result = subprocess.run(
+                    [os.environ.get("PYTHON", sys.executable), "-c", code],
+                    timeout=timeout,
+                    capture_output=True,
+                    text=True,
+                )
+                stdout = "" if silent else result.stdout
+                stderr = result.stderr if result.returncode != 0 else ""
+                return {
+                    "data": {
+                        "output": {"text": stdout, "images": []},
+                        "error": stderr,
+                    }
+                }
+            except subprocess.TimeoutExpired:
+                return {
+                    "data": {
+                        "output": {"text": "", "images": []},
+                        "error": "Execution timed out.",
+                    }
+                }
+
+        return await asyncio.to_thread(_run)
+
+
+@dataclass
+class LocalFileSystemComponent(FileSystemComponent):
+    async def create_file(
+        self, path: str, content: str = "", mode: int = 0o644
+    ) -> dict[str, Any]:
+        def _run() -> dict[str, Any]:
+            abs_path = _ensure_safe_path(path)
+            os.makedirs(os.path.dirname(abs_path), exist_ok=True)
+            with open(abs_path, "w", encoding="utf-8") as f:
+                f.write(content)
+            os.chmod(abs_path, mode)
+            return {"success": True, "path": abs_path}
+
+        return await asyncio.to_thread(_run)
+
+    async def read_file(self, path: str, encoding: str = "utf-8") -> dict[str, Any]:
+        def _run() -> dict[str, Any]:
+            abs_path = _ensure_safe_path(path)
+            with open(abs_path, encoding=encoding) as f:
+                content = f.read()
+            return {"success": True, "content": content}
+
+        return await asyncio.to_thread(_run)
+
+    async def write_file(
+        self, path: str, content: str, mode: str = "w", encoding: str = "utf-8"
+    ) -> dict[str, Any]:
+        def _run() -> dict[str, Any]:
+            abs_path = _ensure_safe_path(path)
+            os.makedirs(os.path.dirname(abs_path), exist_ok=True)
+            with open(abs_path, mode, encoding=encoding) as f:
+                f.write(content)
+            return {"success": True, "path": abs_path}
+
+        return await asyncio.to_thread(_run)
+
+    async def delete_file(self, path: str) -> dict[str, Any]:
+        def _run() -> dict[str, Any]:
+            abs_path = _ensure_safe_path(path)
+            if os.path.isdir(abs_path):
+                shutil.rmtree(abs_path)
+            else:
+                os.remove(abs_path)
+            return {"success": True, "path": abs_path}
+
+        return await asyncio.to_thread(_run)
+
+    async def list_dir(
+        self, path: str = ".", show_hidden: bool = False
+    ) -> dict[str, Any]:
+        def _run() -> dict[str, Any]:
+            abs_path = _ensure_safe_path(path)
+            entries = os.listdir(abs_path)
+            if not show_hidden:
+                entries = [e for e in entries if not e.startswith(".")]
+            return {"success": True, "entries": entries}
+
+        return await asyncio.to_thread(_run)
+
+
+class LocalBooter(ComputerBooter):
+    def __init__(self) -> None:
+        self._fs = LocalFileSystemComponent()
+        self._python = LocalPythonComponent()
+        self._shell = LocalShellComponent()
+
+    async def boot(self, session_id: str) -> None:
+        logger.info(f"Local computer booter initialized for session: {session_id}")
+
+    async def shutdown(self) -> None:
+        logger.info("Local computer booter shutdown complete.")
+
+    @property
+    def fs(self) -> FileSystemComponent:
+        return self._fs
+
+    @property
+    def python(self) -> PythonComponent:
+        return self._python
+
+    @property
+    def shell(self) -> ShellComponent:
+        return self._shell
+
+    async def upload_file(self, path: str, file_name: str) -> dict:
+        raise NotImplementedError(
+            "LocalBooter does not support upload_file operation. Use shell instead."
+        )
+
+    async def download_file(self, remote_path: str, local_path: str):
+        raise NotImplementedError(
+            "LocalBooter does not support download_file operation. Use shell instead."
+        )
+
+    async def available(self) -> bool:
+        return True

astrbot/core/{sandbox → computer}/booters/shipyard.py

@@ -3,10 +3,10 @@ from shipyard import ShipyardClient, Spec
 from astrbot.api import logger
 
 from ..olayer import FileSystemComponent, PythonComponent, ShellComponent
-from .base import SandboxBooter
+from .base import ComputerBooter
 
 
-class ShipyardBooter(SandboxBooter):
+class ShipyardBooter(ComputerBooter):
     def __init__(
         self,
         endpoint_url: str,

astrbot/core/computer/computer_client.py

@@ -0,0 +1,102 @@
+import os
+import shutil
+import uuid
+from pathlib import Path
+
+from astrbot.api import logger
+from astrbot.core.skills.skill_manager import SANDBOX_SKILLS_ROOT
+from astrbot.core.star.context import Context
+from astrbot.core.utils.astrbot_path import (
+    get_astrbot_skills_path,
+    get_astrbot_temp_path,
+)
+
+from .booters.base import ComputerBooter
+from .booters.local import LocalBooter
+
+session_booter: dict[str, ComputerBooter] = {}
+local_booter: ComputerBooter | None = None
+
+
+async def _sync_skills_to_sandbox(booter: ComputerBooter) -> None:
+    skills_root = get_astrbot_skills_path()
+    if not os.path.isdir(skills_root):
+        return
+    if not any(Path(skills_root).iterdir()):
+        return
+
+    temp_dir = get_astrbot_temp_path()
+    os.makedirs(temp_dir, exist_ok=True)
+    zip_base = os.path.join(temp_dir, "skills_bundle")
+    zip_path = f"{zip_base}.zip"
+
+    try:
+        if os.path.exists(zip_path):
+            os.remove(zip_path)
+        shutil.make_archive(zip_base, "zip", skills_root)
+        remote_zip = Path(SANDBOX_SKILLS_ROOT) / "skills.zip"
+        await booter.shell.exec(f"mkdir -p {SANDBOX_SKILLS_ROOT}")
+        upload_result = await booter.upload_file(zip_path, str(remote_zip))
+        if not upload_result.get("success", False):
+            raise RuntimeError("Failed to upload skills bundle to sandbox.")
+        await booter.shell.exec(
+            f"unzip -o {remote_zip} -d {SANDBOX_SKILLS_ROOT} && rm -f {remote_zip}"
+        )
+    finally:
+        if os.path.exists(zip_path):
+            try:
+                os.remove(zip_path)
+            except Exception:
+                logger.warning(f"Failed to remove temp skills zip: {zip_path}")
+
+
+async def get_booter(
+    context: Context,
+    session_id: str,
+) -> ComputerBooter:
+    config = context.get_config(umo=session_id)
+
+    sandbox_cfg = config.get("provider_settings", {}).get("sandbox", {})
+    booter_type = sandbox_cfg.get("booter", "shipyard")
+
+    if session_id in session_booter:
+        booter = session_booter[session_id]
+        if not await booter.available():
+            # rebuild
+            session_booter.pop(session_id, None)
+    if session_id not in session_booter:
+        uuid_str = uuid.uuid5(uuid.NAMESPACE_DNS, session_id).hex
+        if booter_type == "shipyard":
+            from .booters.shipyard import ShipyardBooter
+
+            ep = sandbox_cfg.get("shipyard_endpoint", "")
+            token = sandbox_cfg.get("shipyard_access_token", "")
+            ttl = sandbox_cfg.get("shipyard_ttl", 3600)
+            max_sessions = sandbox_cfg.get("shipyard_max_sessions", 10)
+
+            client = ShipyardBooter(
+                endpoint_url=ep, access_token=token, ttl=ttl, session_num=max_sessions
+            )
+        elif booter_type == "boxlite":
+            from .booters.boxlite import BoxliteBooter
+
+            client = BoxliteBooter()
+        else:
+            raise ValueError(f"Unknown booter type: {booter_type}")
+
+        try:
+            await client.boot(uuid_str)
+            await _sync_skills_to_sandbox(client)
+        except Exception as e:
+            logger.error(f"Error booting sandbox for session {session_id}: {e}")
+            raise e
+
+        session_booter[session_id] = client
+    return session_booter[session_id]
+
+
+def get_local_booter() -> ComputerBooter:
+    global local_booter
+    if local_booter is None:
+        local_booter = LocalBooter()
+    return local_booter

astrbot/core/{sandbox → computer}/tools/__init__.py

@@ -1,10 +1,11 @@
 from .fs import FileDownloadTool, FileUploadTool
-from .python import PythonTool
+from .python import LocalPythonTool, PythonTool
 from .shell import ExecuteShellTool
 
 __all__ = [
     "FileUploadTool",
     "PythonTool",
+    "LocalPythonTool",
     "ExecuteShellTool",
     "FileDownloadTool",
 ]