diff --git a/astrbot/core/astr_main_agent.py b/astrbot/core/astr_main_agent.py index 2b4a04907e..9861e669c4 100644 --- a/astrbot/core/astr_main_agent.py +++ b/astrbot/core/astr_main_agent.py @@ -51,7 +51,7 @@ retrieve_knowledge_base, ) from astrbot.core.conversation_mgr import Conversation -from astrbot.core.message.components import File, Image, Reply +from astrbot.core.message.components import File, Image, Record, Reply from astrbot.core.persona_error_reply import ( extract_persona_custom_error_message_from_persona, set_persona_custom_error_message_on_event, @@ -515,6 +515,18 @@ def _append_quoted_image_attachment(req: ProviderRequest, image_path: str) -> No ) +def _append_audio_attachment(req: ProviderRequest, audio_path: str) -> None: + req.extra_user_content_parts.append( + TextPart(text=f"[Audio Attachment: path {audio_path}]") + ) + + +def _append_quoted_audio_attachment(req: ProviderRequest, audio_path: str) -> None: + req.extra_user_content_parts.append( + TextPart(text=f"[Audio Attachment in quoted message: path {audio_path}]") + ) + + def _get_quoted_message_parser_settings( provider_settings: dict[str, object] | None, ) -> QuotedMessageParserSettings: @@ -753,12 +765,25 @@ def _modalities_fix(provider: Provider, req: ProviderRequest) -> None: "Provider %s does not support image, using placeholder.", provider ) image_count = len(req.image_urls) - placeholder = " ".join(["[图片]"] * image_count) + placeholder = " ".join(["[Image]"] * image_count) if req.prompt: req.prompt = f"{placeholder} {req.prompt}" else: req.prompt = placeholder req.image_urls = [] + if req.audio_urls: + provider_cfg = provider.provider_config.get("modalities", ["audio"]) + if "audio" not in provider_cfg: + logger.debug( + "Provider %s does not support audio, using placeholder.", provider + ) + audio_count = len(req.audio_urls) + placeholder = " ".join(["[Audio]"] * audio_count) + if req.prompt: + req.prompt = f"{placeholder} {req.prompt}" + else: + req.prompt = placeholder + req.audio_urls = [] if req.func_tool: provider_cfg = provider.provider_config.get("modalities", ["tool_use"]) if "tool_use" not in provider_cfg: @@ -781,12 +806,14 @@ def _sanitize_context_by_modalities( if not modalities or not isinstance(modalities, list): return supports_image = bool("image" in modalities) + supports_audio = bool("audio" in modalities) supports_tool_use = bool("tool_use" in modalities) - if supports_image and supports_tool_use: + if supports_image and supports_audio and supports_tool_use: return sanitized_contexts: list[dict] = [] removed_image_blocks = 0 + removed_audio_blocks = 0 removed_tool_messages = 0 removed_tool_calls = 0 @@ -808,20 +835,27 @@ def _sanitize_context_by_modalities( new_msg.pop("tool_calls", None) new_msg.pop("tool_call_id", None) - if not supports_image: + if not supports_image or not supports_audio: content = new_msg.get("content") if isinstance(content, list): filtered_parts: list = [] - removed_any_image = False + removed_any_multimodal = False for part in content: if isinstance(part, dict): part_type = str(part.get("type", "")).lower() - if part_type in {"image_url", "image"}: - removed_any_image = True + if not supports_image and part_type in {"image_url", "image"}: + removed_any_multimodal = True removed_image_blocks += 1 continue + if not supports_audio and part_type in { + "audio_url", + "input_audio", + }: + removed_any_multimodal = True + removed_audio_blocks += 1 + continue filtered_parts.append(part) - if removed_any_image: + if removed_any_multimodal: new_msg["content"] = filtered_parts if role == "assistant": @@ -835,11 +869,18 @@ def _sanitize_context_by_modalities( sanitized_contexts.append(new_msg) - if removed_image_blocks or removed_tool_messages or removed_tool_calls: + if ( + removed_image_blocks + or removed_audio_blocks + or removed_tool_messages + or removed_tool_calls + ): logger.debug( "sanitize_context_by_modalities applied: " - "removed_image_blocks=%s, removed_tool_messages=%s, removed_tool_calls=%s", + "removed_image_blocks=%s, removed_audio_blocks=%s, " + "removed_tool_messages=%s, removed_tool_calls=%s", removed_image_blocks, + removed_audio_blocks, removed_tool_messages, removed_tool_calls, ) @@ -1101,6 +1142,7 @@ async def build_main_agent( req = ProviderRequest() req.prompt = "" req.image_urls = [] + req.audio_urls = [] if sel_model := event.get_extra("selected_model"): req.model = sel_model if config.provider_wake_prefix and not event.message_str.startswith( @@ -1124,6 +1166,10 @@ async def build_main_agent( req.extra_user_content_parts.append( TextPart(text=f"[Image Attachment: path {image_path}]") ) + elif isinstance(comp, Record): + audio_path = await comp.convert_to_file_path() + req.audio_urls.append(audio_path) + _append_audio_attachment(req, audio_path) elif isinstance(comp, File): file_path = await comp.get_file() file_name = comp.name or os.path.basename(file_path) @@ -1155,6 +1201,10 @@ async def build_main_agent( event.track_temporary_local_file(image_path) req.image_urls.append(image_path) _append_quoted_image_attachment(req, image_path) + elif isinstance(reply_comp, Record): + audio_path = await reply_comp.convert_to_file_path() + req.audio_urls.append(audio_path) + _append_quoted_audio_attachment(req, audio_path) elif isinstance(reply_comp, File): file_path = await reply_comp.get_file() file_name = reply_comp.name or os.path.basename(file_path) @@ -1222,6 +1272,7 @@ async def build_main_agent( if isinstance(req.contexts, str): req.contexts = json.loads(req.contexts) req.image_urls = normalize_and_dedupe_strings(req.image_urls) + req.audio_urls = normalize_and_dedupe_strings(req.audio_urls) if config.file_extract_enabled: try: @@ -1229,7 +1280,7 @@ async def build_main_agent( except Exception as exc: # noqa: BLE001 logger.error("Error occurred while applying file extract: %s", exc) - if not req.prompt and not req.image_urls: + if not req.prompt and not req.image_urls and not req.audio_urls: if not event.get_group_id() and req.extra_user_content_parts: req.prompt = "" else: diff --git a/astrbot/core/config/default.py b/astrbot/core/config/default.py index 28971473f7..61a00abd9e 100644 --- a/astrbot/core/config/default.py +++ b/astrbot/core/config/default.py @@ -1874,8 +1874,8 @@ class ChatProviderTemplate(TypedDict): "description": "模型能力", "type": "list", "items": {"type": "string"}, - "options": ["text", "image", "tool_use"], - "labels": ["文本", "图像", "工具使用"], + "options": ["text", "image", "audio", "tool_use"], + "labels": ["文本", "图像", "音频", "工具使用"], "render_type": "checkbox", "hint": "模型支持的模态。如所填写的模型不支持图像，请取消勾选图像。", }, diff --git a/astrbot/core/message/components.py b/astrbot/core/message/components.py index 29bb478da3..2f19434c9d 100644 --- a/astrbot/core/message/components.py +++ b/astrbot/core/message/components.py @@ -64,7 +64,6 @@ class ComponentType(str, Enum): Music = "Music" Json = "Json" Unknown = "Unknown" - WechatEmoji = "WechatEmoji" # Wechat 下的 emoji 表情包 class BaseMessageComponent(BaseModel): @@ -91,7 +90,6 @@ async def to_dict(self) -> dict: class Plain(BaseMessageComponent): type: ComponentType = ComponentType.Plain text: str - convert: bool | None = True def __init__(self, text: str, convert: bool = True, **_) -> None: super().__init__(text=text, convert=convert, **_) @@ -114,11 +112,7 @@ def __init__(self, **_) -> None: class Record(BaseMessageComponent): type: ComponentType = ComponentType.Record file: str | None = "" - magic: bool | None = False url: str | None = "" - cache: bool | None = True - proxy: bool | None = True - timeout: int | None = 0 # Original text content (e.g. TTS source text), used as caption in fallback scenarios text: str | None = None # 额外 @@ -224,7 +218,6 @@ class Video(BaseMessageComponent): type: ComponentType = ComponentType.Video file: str cover: str | None = "" - c: int | None = 2 # 额外 path: str | None = "" @@ -401,14 +394,9 @@ class Image(BaseMessageComponent): type: ComponentType = ComponentType.Image file: str | None = "" _type: str | None = "" - subType: int | None = 0 url: str | None = "" - cache: bool | None = True - id: int | None = 40000 - c: int | None = 2 # 额外 path: str | None = "" - file_unique: str | None = "" # 某些平台可能有图片缓存的唯一标识 def __init__(self, file: str | None, **_) -> None: super().__init__(file=file, **_) @@ -839,16 +827,6 @@ async def to_dict(self): } -class WechatEmoji(BaseMessageComponent): - type: ComponentType = ComponentType.WechatEmoji - md5: str | None = "" - md5_len: int | None = 0 - cdnurl: str | None = "" - - def __init__(self, **_) -> None: - super().__init__(**_) - - ComponentTypes = { # Basic Message Segments "plain": Plain, @@ -874,5 +852,4 @@ def __init__(self, **_) -> None: "nodes": Nodes, "json": Json, "unknown": Unknown, - "WechatEmoji": WechatEmoji, } diff --git a/astrbot/core/pipeline/preprocess_stage/stage.py b/astrbot/core/pipeline/preprocess_stage/stage.py index 0d6d09370e..0f75dfd157 100644 --- a/astrbot/core/pipeline/preprocess_stage/stage.py +++ b/astrbot/core/pipeline/preprocess_stage/stage.py @@ -6,6 +6,7 @@ from astrbot.core import logger from astrbot.core.message.components import Image, Plain, Record from astrbot.core.platform.astr_message_event import AstrMessageEvent +from astrbot.core.utils.media_utils import ensure_wav from ..context import PipelineContext from ..stage import Stage, register_stage @@ -64,6 +65,21 @@ async def process( logger.debug(f"路径映射: {url} -> {component.url}") message_chain[idx] = component + # In here, we convert all Record components to wav format and update the file path. + message_chain = event.get_messages() + for idx, component in enumerate(message_chain): + if isinstance(component, Record): + try: + original_path = await component.convert_to_file_path() + record_path = await ensure_wav(original_path) + if record_path != original_path: + event.track_temporary_local_file(record_path) + component.file = record_path + component.path = record_path + message_chain[idx] = component + except Exception as e: + logger.warning(f"Voice processing failed: {e}") + # STT if self.stt_settings.get("enable", False): # TODO: 独立 diff --git a/astrbot/core/pipeline/process_stage/method/agent_sub_stages/internal.py b/astrbot/core/pipeline/process_stage/method/agent_sub_stages/internal.py index 1a04e3a48e..e0ba2463ca 100644 --- a/astrbot/core/pipeline/process_stage/method/agent_sub_stages/internal.py +++ b/astrbot/core/pipeline/process_stage/method/agent_sub_stages/internal.py @@ -13,7 +13,7 @@ MainAgentBuildResult, build_main_agent, ) -from astrbot.core.message.components import File, Image +from astrbot.core.message.components import File, Image, Record, Video from astrbot.core.message.message_event_result import ( MessageChain, MessageEventResult, @@ -153,7 +153,8 @@ async def process( has_provider_request = event.get_extra("provider_request") is not None has_valid_message = bool(event.message_str and event.message_str.strip()) has_media_content = any( - isinstance(comp, Image | File) for comp in event.message_obj.message + isinstance(comp, (Image, File, Record, Video)) + for comp in event.message_obj.message ) if ( diff --git a/astrbot/core/pipeline/process_stage/method/agent_sub_stages/third_party.py b/astrbot/core/pipeline/process_stage/method/agent_sub_stages/third_party.py index 070ad7bdee..9ab315779c 100644 --- a/astrbot/core/pipeline/process_stage/method/agent_sub_stages/third_party.py +++ b/astrbot/core/pipeline/process_stage/method/agent_sub_stages/third_party.py @@ -17,7 +17,7 @@ ) from astrbot.core.agent.runners.dify.dify_agent_runner import DifyAgentRunner from astrbot.core.astr_agent_hooks import MAIN_AGENT_HOOKS -from astrbot.core.message.components import Image +from astrbot.core.message.components import Image, Record from astrbot.core.message.message_event_result import ( MessageChain, MessageEventResult, @@ -317,8 +317,11 @@ async def process( if isinstance(comp, Image): image_path = await comp.convert_to_base64() req.image_urls.append(image_path) + elif isinstance(comp, Record): + audio_path = await comp.convert_to_file_path() + req.audio_urls.append(audio_path) - if not req.prompt and not req.image_urls: + if not req.prompt and not req.image_urls and not req.audio_urls: return custom_error_message = await self._resolve_persona_custom_error_message(event) diff --git a/astrbot/core/pipeline/respond/stage.py b/astrbot/core/pipeline/respond/stage.py index 6a884a5181..aea6a74b3e 100644 --- a/astrbot/core/pipeline/respond/stage.py +++ b/astrbot/core/pipeline/respond/stage.py @@ -32,7 +32,6 @@ class RespondStage(Stage): Comp.Node: lambda comp: bool(comp.content), # 转发节点 Comp.Nodes: lambda comp: bool(comp.nodes), # 多个转发节点 Comp.File: lambda comp: bool(comp.file_ or comp.url), - Comp.WechatEmoji: lambda comp: comp.md5 is not None, # 微信表情 Comp.Json: lambda comp: bool(comp.data), # Json 卡片 Comp.Share: lambda comp: bool(comp.url) or bool(comp.title), Comp.Music: lambda comp: ( diff --git a/astrbot/core/platform/astr_message_event.py b/astrbot/core/platform/astr_message_event.py index 0ecd47fedc..6454367022 100644 --- a/astrbot/core/platform/astr_message_event.py +++ b/astrbot/core/platform/astr_message_event.py @@ -414,6 +414,7 @@ def request_llm( tool_set: ToolSet | None = None, session_id: str = "", image_urls: list[str] | None = None, + audio_urls: list[str] | None = None, contexts: list | None = None, system_prompt: str = "", conversation: Conversation | None = None, @@ -432,6 +433,8 @@ def request_llm( image_urls: 可以是 base64:// 或者 http:// 开头的图片链接，也可以是本地图片路径。 + audio_urls: 音频 URL 列表，也支持本地路径。 + contexts: 当指定 contexts 时，将会使用 contexts 作为上下文。如果同时传入了 conversation，将会忽略 conversation。 func_tool_manager: [Deprecated] 函数工具管理器，用于调用函数工具。用 self.context.get_llm_tool_manager() 获取。已过时，请使用 tool_set 参数代替。 @@ -441,6 +444,8 @@ def request_llm( """ if image_urls is None: image_urls = [] + if audio_urls is None: + audio_urls = [] if contexts is None: contexts = [] if len(contexts) > 0 and conversation: @@ -450,6 +455,7 @@ def request_llm( prompt=prompt, session_id=session_id, image_urls=image_urls, + audio_urls=audio_urls, # func_tool=func_tool_manager, func_tool=tool_set, contexts=contexts, diff --git a/astrbot/core/provider/entities.py b/astrbot/core/provider/entities.py index 20c5a7947d..b27775cdd7 100644 --- a/astrbot/core/provider/entities.py +++ b/astrbot/core/provider/entities.py @@ -3,8 +3,11 @@ import base64 import enum import json +import uuid from dataclasses import dataclass, field +from pathlib import Path from typing import Any +from urllib.parse import urlparse from anthropic.types import Message as AnthropicMessage from google.genai.types import GenerateContentResponse @@ -21,7 +24,8 @@ from astrbot.core.agent.tool import ToolSet from astrbot.core.db.po import Conversation from astrbot.core.message.message_event_result import MessageChain -from astrbot.core.utils.io import download_image_by_url +from astrbot.core.utils.astrbot_path import get_astrbot_temp_path +from astrbot.core.utils.io import download_file, download_image_by_url class ProviderType(enum.Enum): @@ -93,6 +97,8 @@ class ProviderRequest: """会话 ID""" image_urls: list[str] = field(default_factory=list) """图片 URL 列表""" + audio_urls: list[str] = field(default_factory=list) + """音频 URL 列表，也支持本地路径""" extra_user_content_parts: list[ContentPart] = field(default_factory=list) """额外的用户消息内容部分列表，用于在用户消息后添加额外的内容块（如系统提醒、指令等）。支持 dict 或 ContentPart 对象""" func_tool: ToolSet | None = None @@ -115,6 +121,7 @@ def __repr__(self) -> str: return ( f"ProviderRequest(prompt={self.prompt}, session_id={self.session_id}, " f"image_count={len(self.image_urls or [])}, " + f"audio_count={len(self.audio_urls or [])}, " f"func_tool={self.func_tool}, " f"contexts={self._print_friendly_context()}, " f"system_prompt={self.system_prompt}, " @@ -133,9 +140,12 @@ def append_tool_calls_result(self, tool_calls_result: ToolCallsResult) -> None: self.tool_calls_result.append(tool_calls_result) def _print_friendly_context(self): - """打印友好的消息上下文。将 image_url 的值替换为 """ + """打印友好的消息上下文。将多模态内容折叠为简短标记。""" if not self.contexts: - return f"prompt: {self.prompt}, image_count: {len(self.image_urls or [])}" + return ( + f"prompt: {self.prompt}, image_count: {len(self.image_urls or [])}, " + f"audio_count: {len(self.audio_urls or [])}" + ) result_parts = [] @@ -148,6 +158,7 @@ def _print_friendly_context(self): elif isinstance(content, list): msg_parts = [] image_count = 0 + audio_count = 0 for item in content: item_type = item.get("type", "") @@ -156,19 +167,26 @@ def _print_friendly_context(self): msg_parts.append(item.get("text", "")) elif item_type == "image_url": image_count += 1 + elif item_type == "audio_url": + audio_count += 1 if image_count > 0: if msg_parts: msg_parts.append(f"[+{image_count} images]") else: msg_parts.append(f"[{image_count} images]") + if audio_count > 0: + if msg_parts: + msg_parts.append(f"[+{audio_count} audios]") + else: + msg_parts.append(f"[{audio_count} audios]") result_parts.append(f"{role}: {''.join(msg_parts)}") return "\n".join(result_parts) async def assemble_context(self) -> dict: - """将请求(prompt 和 image_urls)包装成 OpenAI 的消息格式。""" + """将请求(prompt、image_urls 和 audio_urls)包装成统一消息格式。""" # 构建内容块列表 content_blocks = [] @@ -178,6 +196,9 @@ async def assemble_context(self) -> dict: elif self.image_urls: # 如果没有文本但有图片，添加占位文本 content_blocks.append({"type": "text", "text": "[图片]"}) + elif self.audio_urls: + # 如果没有文本但有音频，添加占位文本 + content_blocks.append({"type": "text", "text": "[音频]"}) # 2. 额外的内容块（系统提醒、指令等） if self.extra_user_content_parts: @@ -202,12 +223,57 @@ async def assemble_context(self) -> dict: {"type": "image_url", "image_url": {"url": image_data}}, ) + # 4. 音频内容 + if self.audio_urls: + for audio_url in self.audio_urls: + if audio_url.startswith("http"): + parsed_url = urlparse(audio_url) + suffix = Path(parsed_url.path).suffix + temp_dir = Path(get_astrbot_temp_path()) + temp_dir.mkdir(parents=True, exist_ok=True) + temp_audio_path = ( + temp_dir / f"provider_request_audio_{uuid.uuid4().hex}{suffix}" + ) + try: + await download_file(audio_url, str(temp_audio_path)) + audio_data = await self._encode_audio_bs64( + str(temp_audio_path), + source_ref=audio_url, + ) + finally: + try: + temp_audio_path.unlink(missing_ok=True) + except Exception as exc: + logger.warning( + "Failed to cleanup %s: %s", + temp_audio_path, + exc, + ) + elif audio_url.startswith("file:///"): + audio_path = audio_url.replace("file:///", "") + audio_data = await self._encode_audio_bs64( + audio_path, + source_ref=audio_url, + ) + else: + audio_data = await self._encode_audio_bs64( + audio_url, + source_ref=audio_url, + ) + if not audio_data: + logger.warning(f"音频 {audio_url} 得到的结果为空，将忽略。") + continue + content_blocks.append( + {"type": "audio_url", "audio_url": {"url": audio_data}}, + ) + # 只有当只有一个来自 prompt 的文本块且没有额外内容块时，才降级为简单格式以保持向后兼容 if ( len(content_blocks) == 1 and content_blocks[0]["type"] == "text" and not self.extra_user_content_parts and not self.image_urls + and not self.audio_urls ): return {"role": "user", "content": content_blocks[0]["text"]} @@ -221,7 +287,21 @@ async def _encode_image_bs64(self, image_url: str) -> str: with open(image_url, "rb") as f: image_bs64 = base64.b64encode(f.read()).decode("utf-8") return "data:image/jpeg;base64," + image_bs64 - return "" + + async def _encode_audio_bs64( + self, + audio_path: str, + source_ref: str | None = None, + ) -> str: + """将音频转换为 base64""" + mime_type = "audio/wav" + + if audio_path.startswith("base64://"): + return audio_path.replace("base64://", f"data:{mime_type};base64,", 1) + + with open(audio_path, "rb") as f: + audio_bs64 = base64.b64encode(f.read()).decode("utf-8") + return f"data:{mime_type};base64," + audio_bs64 @dataclass diff --git a/astrbot/core/provider/provider.py b/astrbot/core/provider/provider.py index fab3ce6104..f2571b506c 100644 --- a/astrbot/core/provider/provider.py +++ b/astrbot/core/provider/provider.py @@ -98,6 +98,7 @@ async def text_chat( prompt: str | None = None, session_id: str | None = None, image_urls: list[str] | None = None, + audio_urls: list[str] | None = None, func_tool: ToolSet | None = None, contexts: list[Message] | list[dict] | None = None, system_prompt: str | None = None, @@ -113,6 +114,7 @@ async def text_chat( prompt: 提示词，和 contexts 二选一使用，如果都指定，则会将 prompt（以及可能的 image_urls） 作为最新的一条记录添加到 contexts 中 session_id: 会话 ID(此属性已经被废弃) image_urls: 图片 URL 列表 + audio_urls: 音频 URL 列表，也支持本地路径 tools: tool set tool_choice: 工具调用策略，`auto` 表示由模型自行决定，`required` 表示要求模型必须调用工具 contexts: 上下文，和 prompt 二选一使用 @@ -122,6 +124,7 @@ async def text_chat( Notes: - 如果传入了 image_urls，将会在对话时附上图片。如果模型不支持图片输入，将会抛出错误。 + - 如果传入了 audio_urls，将会在对话时附上音频。如果模型不支持音频输入，将会抛出错误或降级处理。 - 如果传入了 tools，将会使用 tools 进行 Function-calling。如果模型不支持 Function-calling，将会抛出错误。 """ @@ -132,6 +135,7 @@ async def text_chat_stream( prompt: str | None = None, session_id: str | None = None, image_urls: list[str] | None = None, + audio_urls: list[str] | None = None, func_tool: ToolSet | None = None, contexts: list[Message] | list[dict] | None = None, system_prompt: str | None = None, @@ -146,6 +150,7 @@ async def text_chat_stream( prompt: 提示词，和 contexts 二选一使用，如果都指定，则会将 prompt（以及可能的 image_urls） 作为最新的一条记录添加到 contexts 中 session_id: 会话 ID(此属性已经被废弃) image_urls: 图片 URL 列表 + audio_urls: 音频 URL 列表，也支持本地路径 tools: tool set tool_choice: 工具调用策略，`auto` 表示由模型自行决定，`required` 表示要求模型必须调用工具 contexts: 上下文，和 prompt 二选一使用 @@ -154,6 +159,7 @@ async def text_chat_stream( Notes: - 如果传入了 image_urls，将会在对话时附上图片。如果模型不支持图片输入，将会抛出错误。 + - 如果传入了 audio_urls，将会在对话时附上音频。如果模型不支持音频输入，将会抛出错误或降级处理。 - 如果传入了 tools，将会使用 tools 进行 Function-calling。如果模型不支持 Function-calling，将会抛出错误。 """ diff --git a/astrbot/core/provider/sources/anthropic_source.py b/astrbot/core/provider/sources/anthropic_source.py index 89c33021ae..83f2e16dba 100644 --- a/astrbot/core/provider/sources/anthropic_source.py +++ b/astrbot/core/provider/sources/anthropic_source.py @@ -12,7 +12,7 @@ from astrbot import logger from astrbot.api.provider import Provider -from astrbot.core.agent.message import ContentPart, ImageURLPart, TextPart +from astrbot.core.agent.message import AudioURLPart, ContentPart, ImageURLPart, TextPart from astrbot.core.exceptions import EmptyModelOutputError from astrbot.core.provider.entities import LLMResponse, TokenUsage from astrbot.core.provider.func_tool_manager import ToolSet @@ -242,6 +242,13 @@ def _prepare_payload(self, messages: list[dict]): logger.warning( f"Unsupported image URL format for Anthropic: {url[:50]}..." ) + elif part.get("type") == "audio_url": + converted_content.append( + { + "type": "text", + "text": "[Audio Attachment]", + } + ) else: converted_content.append(part) new_messages.append( @@ -517,6 +524,7 @@ async def text_chat( prompt=None, session_id=None, image_urls=None, + audio_urls=None, func_tool=None, contexts=None, system_prompt=None, @@ -531,7 +539,10 @@ async def text_chat( new_record = None if prompt is not None: new_record = await self.assemble_context( - prompt, image_urls, extra_user_content_parts + prompt or "", + image_urls, + audio_urls, + extra_user_content_parts, ) context_query = self._ensure_message_to_dicts(contexts) if new_record: @@ -577,6 +588,7 @@ async def text_chat_stream( prompt=None, session_id=None, image_urls=None, + audio_urls=None, func_tool=None, contexts=None, system_prompt=None, @@ -591,7 +603,10 @@ async def text_chat_stream( new_record = None if prompt is not None: new_record = await self.assemble_context( - prompt, image_urls, extra_user_content_parts + prompt or "", + image_urls, + audio_urls, + extra_user_content_parts, ) context_query = self._ensure_message_to_dicts(contexts) if new_record: @@ -642,6 +657,7 @@ async def assemble_context( self, text: str, image_urls: list[str] | None = None, + audio_urls: list[str] | None = None, extra_user_content_parts: list[ContentPart] | None = None, ): """组装上下文，支持文本和图片""" @@ -680,7 +696,9 @@ async def resolve_image_url(image_url: str) -> dict | None: content.append({"type": "text", "text": text}) elif image_urls: # 如果没有文本但有图片，添加占位文本 - content.append({"type": "text", "text": "[图片]"}) + content.append({"type": "text", "text": "[Image]"}) + elif audio_urls: + content.append({"type": "text", "text": "[Audio]"}) elif extra_user_content_parts: # 如果只有额外内容块，也需要添加占位文本 content.append({"type": "text", "text": " "}) @@ -694,6 +712,8 @@ async def resolve_image_url(image_url: str) -> dict | None: image_dict = await resolve_image_url(block.image_url.url) if image_dict: content.append(image_dict) + elif isinstance(block, AudioURLPart): + content.append({"type": "text", "text": "[Audio]"}) else: raise ValueError(f"不支持的额外内容块类型: {type(block)}") @@ -703,12 +723,16 @@ async def resolve_image_url(image_url: str) -> dict | None: image_dict = await resolve_image_url(image_url) if image_dict: content.append(image_dict) + if audio_urls: + for _audio_path in audio_urls: + content.append({"type": "text", "text": "[Audio]"}) # 如果只有主文本且没有额外内容块和图片，返回简单格式以保持向后兼容 if ( text and not extra_user_content_parts and not image_urls + and not audio_urls and len(content) == 1 and content[0]["type"] == "text" ): diff --git a/astrbot/core/provider/sources/gemini_source.py b/astrbot/core/provider/sources/gemini_source.py index 1f447c85bd..e5fae456dc 100644 --- a/astrbot/core/provider/sources/gemini_source.py +++ b/astrbot/core/provider/sources/gemini_source.py @@ -3,8 +3,11 @@ import json import logging import random +import uuid from collections.abc import AsyncGenerator +from pathlib import Path from typing import Literal, cast +from urllib.parse import urlparse from google import genai from google.genai import types @@ -13,12 +16,14 @@ import astrbot.core.message.components as Comp from astrbot import logger from astrbot.api.provider import Provider -from astrbot.core.agent.message import ContentPart, ImageURLPart, TextPart +from astrbot.core.agent.message import AudioURLPart, ContentPart, ImageURLPart, TextPart from astrbot.core.exceptions import EmptyModelOutputError from astrbot.core.message.message_event_result import MessageChain from astrbot.core.provider.entities import LLMResponse, TokenUsage from astrbot.core.provider.func_tool_manager import ToolSet -from astrbot.core.utils.io import download_image_by_url +from astrbot.core.utils.astrbot_path import get_astrbot_temp_path +from astrbot.core.utils.io import download_file, download_image_by_url +from astrbot.core.utils.media_utils import ensure_wav from astrbot.core.utils.network_utils import is_connection_error, log_connection_failure from ..register import register_provider_adapter @@ -304,6 +309,12 @@ def process_image_url(image_url_dict: dict) -> types.Part: image_bytes = base64.b64decode(url.split(",", 1)[1]) return types.Part.from_bytes(data=image_bytes, mime_type=mime_type) + def process_audio_url(audio_url_dict: dict) -> types.Part: + url = audio_url_dict["url"] + mime_type = url.split(":")[1].split(";")[0] + audio_bytes = base64.b64decode(url.split(",", 1)[1]) + return types.Part.from_bytes(data=audio_bytes, mime_type=mime_type) + def append_or_extend( contents: list[types.Content], part: list[types.Part], @@ -331,7 +342,11 @@ def append_or_extend( ( types.Part.from_text(text=item["text"] or " ") if item["type"] == "text" - else process_image_url(item["image_url"]) + else ( + process_image_url(item["image_url"]) + if item["type"] == "image_url" + else process_audio_url(item["audio_url"]) + ) ) for item in content ] @@ -782,6 +797,7 @@ async def text_chat( prompt=None, session_id=None, image_urls=None, + audio_urls=None, func_tool=None, contexts=None, system_prompt=None, @@ -796,7 +812,10 @@ async def text_chat( new_record = None if prompt is not None: new_record = await self.assemble_context( - prompt, image_urls, extra_user_content_parts + prompt or "", + image_urls, + audio_urls, + extra_user_content_parts, ) context_query = self._ensure_message_to_dicts(contexts) if new_record: @@ -840,6 +859,7 @@ async def text_chat_stream( prompt=None, session_id=None, image_urls=None, + audio_urls=None, func_tool=None, contexts=None, system_prompt=None, @@ -854,7 +874,10 @@ async def text_chat_stream( new_record = None if prompt is not None: new_record = await self.assemble_context( - prompt, image_urls, extra_user_content_parts + prompt or "", + image_urls, + audio_urls, + extra_user_content_parts, ) context_query = self._ensure_message_to_dicts(contexts) if new_record: @@ -920,6 +943,7 @@ async def assemble_context( self, text: str, image_urls: list[str] | None = None, + audio_urls: list[str] | None = None, extra_user_content_parts: list[ContentPart] | None = None, ): """组装上下文。""" @@ -941,6 +965,43 @@ async def resolve_image_part(image_url: str) -> dict | None: "image_url": {"url": image_data}, } + async def resolve_audio_part(audio_path: str) -> dict | None: + if audio_path.startswith("http"): + suffix = Path(urlparse(audio_path).path).suffix or ".wav" + temp_dir = Path(get_astrbot_temp_path()) + temp_dir.mkdir(parents=True, exist_ok=True) + resolved_path = str( + temp_dir / f"provider_audio_{uuid.uuid4().hex}{suffix}" + ) + await download_file(audio_path, resolved_path) + elif audio_path.startswith("file:///"): + resolved_path = audio_path.replace("file:///", "") + else: + resolved_path = audio_path + + suffix = Path(resolved_path).suffix.lower() + if suffix != ".mp3": + resolved_path = await ensure_wav(resolved_path) + suffix = ".wav" + + try: + audio_bytes = Path(resolved_path).read_bytes() + except OSError as exc: + logger.warning( + f"Failed to read audio file {resolved_path}, skipping. Error: {exc}" + ) + return None + + mime_type = { + ".wav": "audio/wav", + ".mp3": "audio/mp3", + }.get(suffix, "audio/wav") + audio_data = base64.b64encode(audio_bytes).decode("utf-8") + return { + "type": "audio_url", + "audio_url": {"url": f"data:{mime_type};base64,{audio_data}"}, + } + # 构建内容块列表 content_blocks = [] @@ -949,7 +1010,9 @@ async def resolve_image_part(image_url: str) -> dict | None: content_blocks.append({"type": "text", "text": text}) elif image_urls: # 如果没有文本但有图片，添加占位文本 - content_blocks.append({"type": "text", "text": "[图片]"}) + content_blocks.append({"type": "text", "text": "[Image]"}) + elif audio_urls: + content_blocks.append({"type": "text", "text": "[Audio]"}) elif extra_user_content_parts: # 如果只有额外内容块，也需要添加占位文本 content_blocks.append({"type": "text", "text": " "}) @@ -963,6 +1026,10 @@ async def resolve_image_part(image_url: str) -> dict | None: image_part = await resolve_image_part(part.image_url.url) if image_part: content_blocks.append(image_part) + elif isinstance(part, AudioURLPart): + audio_part = await resolve_audio_part(part.audio_url.url) + if audio_part: + content_blocks.append(audio_part) else: raise ValueError(f"不支持的额外内容块类型: {type(part)}") @@ -973,11 +1040,18 @@ async def resolve_image_part(image_url: str) -> dict | None: if image_part: content_blocks.append(image_part) + if audio_urls: + for audio_path in audio_urls: + audio_part = await resolve_audio_part(audio_path) + if audio_part: + content_blocks.append(audio_part) + # 如果只有主文本且没有额外内容块和图片，返回简单格式以保持向后兼容 if ( text and not extra_user_content_parts and not image_urls + and not audio_urls and len(content_blocks) == 1 and content_blocks[0]["type"] == "text" ): diff --git a/astrbot/core/provider/sources/openai_source.py b/astrbot/core/provider/sources/openai_source.py index 33432b6636..b19f3460dd 100644 --- a/astrbot/core/provider/sources/openai_source.py +++ b/astrbot/core/provider/sources/openai_source.py @@ -5,6 +5,7 @@ import json import random import re +import uuid from collections.abc import AsyncGenerator from io import BytesIO from pathlib import Path @@ -24,12 +25,20 @@ import astrbot.core.message.components as Comp from astrbot import logger from astrbot.api.provider import Provider -from astrbot.core.agent.message import ContentPart, ImageURLPart, Message, TextPart +from astrbot.core.agent.message import ( + AudioURLPart, + ContentPart, + ImageURLPart, + Message, + TextPart, +) from astrbot.core.agent.tool import ToolSet from astrbot.core.exceptions import EmptyModelOutputError from astrbot.core.message.message_event_result import MessageChain from astrbot.core.provider.entities import LLMResponse, TokenUsage, ToolCallsResult -from astrbot.core.utils.io import download_image_by_url +from astrbot.core.utils.astrbot_path import get_astrbot_temp_path +from astrbot.core.utils.io import download_file, download_image_by_url +from astrbot.core.utils.media_utils import ensure_wav from astrbot.core.utils.network_utils import ( create_proxy_client, is_connection_error, @@ -136,7 +145,10 @@ def _context_contains_image(contexts: list[dict]) -> bool: if not isinstance(content, list): continue for item in content: - if isinstance(item, dict) and item.get("type") == "image_url": + if isinstance(item, dict) and item.get("type") in { + "image_url", + "audio_url", + }: return True return False @@ -285,24 +297,103 @@ def _extract_image_part_info(self, part: dict) -> tuple[str | None, str | None]: image_detail = None return url, image_detail - async def _transform_content_part(self, part: dict) -> dict: - url, image_detail = self._extract_image_part_info(part) - if not url: - return part + def _extract_audio_part_info(self, part: dict) -> str | None: + if not isinstance(part, dict) or part.get("type") != "audio_url": + return None + audio_url_data = part.get("audio_url") + if not isinstance(audio_url_data, dict): + logger.warning("音频内容块格式无效，将保留原始内容。") + return None + + url = audio_url_data.get("url") + if not isinstance(url, str) or not url: + logger.warning("音频内容块缺少有效路径，将保留原始内容。") + return None + + return url + + async def _audio_ref_to_local_path(self, audio_ref: str) -> tuple[str, list[Path]]: + cleanup_paths: list[Path] = [] + if audio_ref.startswith("http"): + suffix = Path(urlparse(audio_ref).path).suffix or ".wav" + temp_dir = Path(get_astrbot_temp_path()) + temp_dir.mkdir(parents=True, exist_ok=True) + target_path = temp_dir / f"provider_audio_{uuid.uuid4().hex}{suffix}" + await download_file(audio_ref, str(target_path)) + cleanup_paths.append(target_path) + return str(target_path), cleanup_paths + if audio_ref.startswith("file://"): + return self._file_uri_to_path(audio_ref), cleanup_paths + return audio_ref, cleanup_paths + + async def _resolve_audio_part(self, audio_ref: str) -> dict | None: + cleanup_paths: list[Path] = [] try: - resolved_part = await self._resolve_image_part( - url, image_detail=image_detail - ) + audio_path, cleanup_paths = await self._audio_ref_to_local_path(audio_ref) + suffix = Path(audio_path).suffix.lower() + if suffix == ".mp3": + audio_format = "mp3" + else: + converted_audio_path = await ensure_wav(audio_path) + if converted_audio_path != audio_path: + cleanup_paths.append(Path(converted_audio_path)) + audio_path = converted_audio_path + audio_format = "wav" + audio_bytes = Path(audio_path).read_bytes() except Exception as exc: - logger.warning( - "图片 %s 预处理失败，将保留原始内容。错误: %s", - url, - exc, - ) + logger.warning("音频 %s 预处理失败，将忽略。错误: %s", audio_ref, exc) + return None + finally: + for cleanup_path in cleanup_paths: + try: + cleanup_path.unlink(missing_ok=True) + except Exception as cleanup_exc: + logger.warning( + "Failed to cleanup %s: %s", + cleanup_path, + cleanup_exc, + ) + + return { + "type": "input_audio", + "input_audio": { + "data": base64.b64encode(audio_bytes).decode("utf-8"), + "format": audio_format, + }, + } + + async def _transform_content_part(self, part: dict) -> dict: + if not isinstance(part, dict): return part - return resolved_part or part + if part.get("type") == "image_url": + url, image_detail = self._extract_image_part_info(part) + if not url: + return part + + try: + resolved_part = await self._resolve_image_part( + url, image_detail=image_detail + ) + except Exception as exc: + logger.warning( + "图片 %s 预处理失败，将保留原始内容。错误: %s", + url, + exc, + ) + return part + + return resolved_part or part + + if part.get("type") == "audio_url": + audio_ref = self._extract_audio_part_info(part) + if not audio_ref: + return part + resolved_part = await self._resolve_audio_part(audio_ref) + return resolved_part or part + + return part async def _materialize_message_image_parts(self, message: dict) -> dict: content = message.get("content") @@ -816,6 +907,7 @@ async def _prepare_chat_payload( self, prompt: str | None, image_urls: list[str] | None = None, + audio_urls: list[str] | None = None, contexts: list[dict] | list[Message] | None = None, system_prompt: str | None = None, tool_calls_result: ToolCallsResult | list[ToolCallsResult] | None = None, @@ -829,7 +921,10 @@ async def _prepare_chat_payload( new_record = None if prompt is not None: new_record = await self.assemble_context( - prompt, image_urls, extra_user_content_parts + prompt or "", + image_urls, + audio_urls, + extra_user_content_parts, ) context_query = copy.deepcopy(self._ensure_message_to_dicts(contexts)) if new_record: @@ -1016,6 +1111,7 @@ async def text_chat( prompt=None, session_id=None, image_urls=None, + audio_urls=None, func_tool=None, contexts=None, system_prompt=None, @@ -1028,6 +1124,7 @@ async def text_chat( payloads, context_query = await self._prepare_chat_payload( prompt, image_urls, + audio_urls, contexts, system_prompt, tool_calls_result, @@ -1087,6 +1184,7 @@ async def text_chat_stream( prompt=None, session_id=None, image_urls=None, + audio_urls=None, func_tool=None, contexts=None, system_prompt=None, @@ -1099,6 +1197,7 @@ async def text_chat_stream( payloads, context_query = await self._prepare_chat_payload( prompt, image_urls, + audio_urls, contexts, system_prompt, tool_calls_result, @@ -1183,6 +1282,7 @@ async def assemble_context( self, text: str, image_urls: list[str] | None = None, + audio_urls: list[str] | None = None, extra_user_content_parts: list[ContentPart] | None = None, ) -> dict: """组装成符合 OpenAI 格式的 role 为 user 的消息段""" @@ -1195,7 +1295,9 @@ async def assemble_context( content_blocks.append({"type": "text", "text": text}) elif image_urls: # 如果没有文本但有图片，添加占位文本 - content_blocks.append({"type": "text", "text": "[图片]"}) + content_blocks.append({"type": "text", "text": "[Image]"}) + elif audio_urls: + content_blocks.append({"type": "text", "text": "[Audio]"}) elif extra_user_content_parts: # 如果只有额外内容块，也需要添加占位文本 content_blocks.append({"type": "text", "text": " "}) @@ -1211,6 +1313,10 @@ async def assemble_context( ) if image_part: content_blocks.append(image_part) + elif isinstance(part, AudioURLPart): + audio_part = await self._resolve_audio_part(part.audio_url.url) + if audio_part: + content_blocks.append(audio_part) else: raise ValueError(f"不支持的额外内容块类型: {type(part)}") @@ -1221,11 +1327,18 @@ async def assemble_context( if image_part: content_blocks.append(image_part) + if audio_urls: + for audio_path in audio_urls: + audio_part = await self._resolve_audio_part(audio_path) + if audio_part: + content_blocks.append(audio_part) + # 如果只有主文本且没有额外内容块和图片，返回简单格式以保持向后兼容 if ( text and not extra_user_content_parts and not image_urls + and not audio_urls and len(content_blocks) == 1 and content_blocks[0]["type"] == "text" ): diff --git a/astrbot/core/star/context.py b/astrbot/core/star/context.py index 606f46dd73..058cf61e54 100644 --- a/astrbot/core/star/context.py +++ b/astrbot/core/star/context.py @@ -107,6 +107,7 @@ async def llm_generate( chat_provider_id: str, prompt: str | None = None, image_urls: list[str] | None = None, + audio_urls: list[str] | None = None, tools: ToolSet | None = None, system_prompt: str | None = None, contexts: list[Message] | None = None, @@ -120,6 +121,7 @@ async def llm_generate( chat_provider_id: The chat provider ID to use. prompt: The prompt to send to the LLM, if `contexts` and `prompt` are both provided, `prompt` will be appended as the last user message image_urls: List of image URLs to include in the prompt, if `contexts` and `prompt` are both provided, `image_urls` will be appended to the last user message + audio_urls: List of audio URLs or local paths to include in the prompt, if `contexts` and `prompt` are both provided, `audio_urls` will be appended to the last user message tools: ToolSet of tools available to the LLM system_prompt: System prompt to guide the LLM's behavior, if provided, it will always insert as the first system message in the context contexts: context messages for the LLM @@ -135,6 +137,7 @@ async def llm_generate( llm_resp = await prov.text_chat( prompt=prompt, image_urls=image_urls, + audio_urls=audio_urls, func_tool=tools, contexts=contexts, system_prompt=system_prompt, @@ -149,6 +152,7 @@ async def tool_loop_agent( chat_provider_id: str, prompt: str | None = None, image_urls: list[str] | None = None, + audio_urls: list[str] | None = None, tools: ToolSet | None = None, system_prompt: str | None = None, contexts: list[Message] | None = None, @@ -165,6 +169,7 @@ async def tool_loop_agent( chat_provider_id: The chat provider ID to use. prompt: The prompt to send to the LLM, if `contexts` and `prompt` are both provided, `prompt` will be appended as the last user message image_urls: List of image URLs to include in the prompt, if `contexts` and `prompt` are both provided, `image_urls` will be appended to the last user message + audio_urls: List of audio URLs or local paths to include in the prompt, if `contexts` and `prompt` are both provided, `audio_urls` will be appended to the last user message tools: ToolSet of tools available to the LLM system_prompt: System prompt to guide the LLM's behavior, if provided, it will always insert as the first system message in the context contexts: context messages for the LLM @@ -207,6 +212,7 @@ async def tool_loop_agent( request = ProviderRequest( prompt=prompt, image_urls=image_urls or [], + audio_urls=audio_urls or [], func_tool=tools, contexts=context_, system_prompt=system_prompt or "", diff --git a/astrbot/core/utils/media_utils.py b/astrbot/core/utils/media_utils.py index d3f3cc75d3..40f1e60495 100644 --- a/astrbot/core/utils/media_utils.py +++ b/astrbot/core/utils/media_utils.py @@ -229,7 +229,7 @@ async def convert_audio_format( Args: audio_path: 原始音频文件路径 - output_format: 目标格式，例如 amr / ogg + output_format: 目标格式，例如 amr / ogg / opus / wav output_path: 输出文件路径，如果为None则自动生成 Returns: @@ -248,6 +248,8 @@ async def convert_audio_format( args.extend(["-ac", "1", "-ar", "8000", "-ab", "12.2k"]) elif output_format == "ogg": args.extend(["-acodec", "libopus", "-ac", "1", "-ar", "16000"]) + elif output_format == "opus": + args.extend(["-acodec", "libopus", "-ac", "1", "-ar", "16000"]) args.append(output_path) try: @@ -289,11 +291,67 @@ async def convert_audio_to_wav(audio_path: str, output_path: str | None = None) ) +async def ensure_wav(audio_path: str, output_path: str | None = None) -> str: + """Ensure the audio path points to wav format by extension/guess and convert when needed. + + If the file appears to already be wav, return it directly to avoid extra conversion. + """ + + if not audio_path: + return audio_path + + if _get_audio_magic_type(audio_path) == "wav": + return audio_path + + return await convert_audio_to_wav(audio_path, output_path) + + +def _get_audio_magic_type(audio_path: str) -> str: + """Detect common audio formats from magic bytes.""" + try: + with open(audio_path, "rb") as f: + header = f.read(64) + except FileNotFoundError: + logger.warning(f"[Media Utils] wav check file not found: {audio_path}") + return "" + except Exception as e: + logger.warning(f"[Media Utils] wav check failed: {audio_path}, error: {e}") + return "" + + if len(header) < 12: + return "" + + if header[:4] == b"RIFF" and header[8:12] == b"WAVE": + return "wav" + + if header[:4] == b"#!AM": + return "amr" + + if header[:4] == b"OggS": + if b"OpusHead" in header: + return "opus" + return "ogg" + + if header[:3] == b"fLa": + return "flac" + + if header[:3] == b"ID3" or header[:2] == b"\xff\xfb": + return "mp3" + + if header[:4] == b"ftyp" and b"mp4" in header[:8]: + return "mp4" + + if header[:8] == b"#!SILK_V3": + return "silk" + + return "" + + async def extract_video_cover( video_path: str, output_path: str | None = None, ) -> str: - """从视频中提取封面图（JPG）。""" + """从视频中提取封面图(JPG)""" if output_path is None: temp_dir = Path(get_astrbot_temp_path()) temp_dir.mkdir(parents=True, exist_ok=True) diff --git a/dashboard/src/assets/mdi-subset/materialdesignicons-subset.css b/dashboard/src/assets/mdi-subset/materialdesignicons-subset.css index 3baa7d48ed..da960e963a 100644 --- a/dashboard/src/assets/mdi-subset/materialdesignicons-subset.css +++ b/dashboard/src/assets/mdi-subset/materialdesignicons-subset.css @@ -1,4 +1,4 @@ -/* Auto-generated MDI subset – 255 icons */ +/* Auto-generated MDI subset – 256 icons */ /* Do not edit manually. Run: pnpm run subset-icons */ @font-face { @@ -684,6 +684,10 @@ content: "\F0375"; } +.mdi-music-note-outline::before { + content: "\F0F74"; +} + .mdi-note-text-outline::before { content: "\F11D7"; } diff --git a/dashboard/src/assets/mdi-subset/materialdesignicons-webfont-subset.woff b/dashboard/src/assets/mdi-subset/materialdesignicons-webfont-subset.woff index 1c3a7f0274..2027f555ad 100644 Binary files a/dashboard/src/assets/mdi-subset/materialdesignicons-webfont-subset.woff and b/dashboard/src/assets/mdi-subset/materialdesignicons-webfont-subset.woff differ diff --git a/dashboard/src/assets/mdi-subset/materialdesignicons-webfont-subset.woff2 b/dashboard/src/assets/mdi-subset/materialdesignicons-webfont-subset.woff2 index 923b8a10a7..79b3946fbc 100644 Binary files a/dashboard/src/assets/mdi-subset/materialdesignicons-webfont-subset.woff2 and b/dashboard/src/assets/mdi-subset/materialdesignicons-webfont-subset.woff2 differ diff --git a/dashboard/src/components/chat/ProviderConfigDialog.vue b/dashboard/src/components/chat/ProviderConfigDialog.vue index 51ff37677f..359bcecdbd 100644 --- a/dashboard/src/components/chat/ProviderConfigDialog.vue +++ b/dashboard/src/components/chat/ProviderConfigDialog.vue @@ -63,6 +63,7 @@ mdi-eye-outline + + +