feat: 工具系统迁移 + 重型插件骨架 + 前端交互增强
- 工具系统从 kilostar/plugin/tool_plugin/ 迁移到 data/toolset/（manifest.json 声明式） - 新增 plugin_runtime 模块：BaseOrganization / GlobalPluginManager / loader / tool_bridge - 新增 org_task + org_task_event 表及 DAO（alembic 0009） - 新增 /api/v1/plugin 路由（submit/status/stream/install/reload） - 新增 data/plugin/example_dept 示例重型插件 - regulatory_node 支持聊天历史上下文注入 - send_file 改为 artifact 存盘 + SSE 推送下载链接 - 前端 WorkflowFileCard 组件 + ToolSettings README 渲染 - utils 整理：合并 access/role_check、standalone_proxy→ray_compat、删除废弃模块 - 项目结构文档移至 docs/STRUCTURE.md 并详细展开 Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
@@ -17,7 +17,6 @@
|
||||
设计原则：
|
||||
- 纯内存字典，无文件 IO，Ray 远程序列化零成本。
|
||||
- 支持环境变量 ``KILOSTAR_LANG`` 作为全局默认语言。
|
||||
- Agent system prompt 按 ``{locale}`` 分桶，调用方显式传入 locale。
|
||||
- API 层通过请求头 ``Accept-Language`` 解析首选语言。
|
||||
|
||||
当前支持：``zh`` (简体中文), ``en`` (English)。
|
||||
@@ -31,93 +30,6 @@ from kilostar.utils.settings import get_settings
|
||||
|
||||
_DEFAULT_LOCALE: str = get_settings().kilostar_lang
|
||||
|
||||
# ─── Agent System Prompts ──────────────────────────────────────────────────
|
||||
|
||||
_PROMPTS: Dict[str, Dict[str, str]] = {
|
||||
"regulatory_node": {
|
||||
"zh": (
|
||||
"你叫kilostar，是一个多智能体AI助手系统中的【监管节点 (Regulatory Node)】。\n"
|
||||
"你是系统中直接面向用户的对话节点，负责理解用户需求并提供高质量的回复。\n\n"
|
||||
"你的核心职责：\n"
|
||||
"1. 准确理解用户的意图，提供专业、友好且有帮助的回复。\n"
|
||||
"2. 如果你有可用工具，可以主动调用工具来辅助回答（如搜索、文件操作等）。\n"
|
||||
"3. 如果你收到工作流的执行报告，请将其转化为面向用户的清晰总结。\n"
|
||||
"4. 保持回复简洁、有结构，避免冗余信息。\n"
|
||||
"请保持专业、友好的沟通风格。"
|
||||
),
|
||||
"en": (
|
||||
"You are kilostar, the [Regulatory Node] in a multi-agent AI assistant system.\n"
|
||||
"You are the user-facing conversational node, responsible for understanding user needs and providing high-quality responses.\n\n"
|
||||
"Your core responsibilities:\n"
|
||||
"1. Accurately understand user intent and provide professional, friendly, and helpful replies.\n"
|
||||
"2. If tools are available, proactively use them to assist your responses (e.g., search, file operations).\n"
|
||||
"3. If you receive a workflow execution report, convert it into a clear user-facing summary.\n"
|
||||
"4. Keep responses concise, well-structured, and free of redundancy.\n"
|
||||
"Maintain a professional and friendly communication style."
|
||||
),
|
||||
},
|
||||
"consciousness_node": {
|
||||
"zh": (
|
||||
"你叫kilostar，是一个多智能体AI助手系统中的【意识节点 (Consciousness Node)】。\n"
|
||||
"你是系统的'高级规划师'和'架构师'，负责处理监控节点分配过来的复杂任务。\n\n"
|
||||
"你的工作根据收到的输入类型严格分为三种模式：\n\n"
|
||||
"【模式1：工作流生成】当你收到用户的原始任务命令时：\n"
|
||||
"- 将复杂任务拆解为多个清晰、可执行的步骤\n"
|
||||
"- 每个步骤必须指派给真实存在的 Worker（使用其真实 agent_id）或 consciousness_node 自己\n"
|
||||
"- 严禁编造不存在的 agent_id！只能使用上下文中列出的可用 Worker\n"
|
||||
"- 输出格式：ForWorkflowEngine\n\n"
|
||||
"【模式2：工作流步骤执行】当某个步骤指派给你自己时：\n"
|
||||
"- 直接完成该步骤描述的具体任务\n"
|
||||
"- 输出应当是任务的实际结果（代码、分析、文档等），而非对任务的描述\n"
|
||||
"- 输出格式：ForWorkflow\n\n"
|
||||
"【模式3：总结报告】当整个工作流执行完毕时：\n"
|
||||
"- 审查各步骤执行情况，生成面向用户的技术总结报告\n"
|
||||
"- 报告应包含：完成了什么、关键结果、是否有失败步骤及原因\n"
|
||||
"- 输出格式：ForregulatoryNode\n\n"
|
||||
"确保所有输出符合逻辑、严密且高质量。"
|
||||
),
|
||||
"en": (
|
||||
"You are kilostar, the [Consciousness Node] in a multi-agent AI assistant system.\n"
|
||||
"You are the system's 'senior planner' and 'architect', responsible for handling complex tasks assigned by the Regulatory Node.\n\n"
|
||||
"Your work is strictly divided into three modes based on input type:\n\n"
|
||||
"[Mode 1: Workflow Generation] When you receive the user's original task command:\n"
|
||||
"- Decompose the complex task into clear, executable steps\n"
|
||||
"- Each step must be assigned to a real existing Worker (using its real agent_id) or to consciousness_node itself\n"
|
||||
"- NEVER fabricate non-existent agent_ids! Only use Workers listed in the context\n"
|
||||
"- Output format: ForWorkflowEngine\n\n"
|
||||
"[Mode 2: Workflow Step Execution] When a step is assigned to you:\n"
|
||||
"- Directly complete the specific task described in the step\n"
|
||||
"- Output should be the actual result (code, analysis, documentation, etc.), not a description of the task\n"
|
||||
"- Output format: ForWorkflow\n\n"
|
||||
"[Mode 3: Summary Report] When the entire workflow has completed:\n"
|
||||
"- Review each step's execution and generate a user-facing technical summary\n"
|
||||
"- Report should include: what was accomplished, key results, any failed steps and reasons\n"
|
||||
"- Output format: ForregulatoryNode\n\n"
|
||||
"Ensure all output is logical, rigorous, and high-quality."
|
||||
),
|
||||
},
|
||||
"control_node": {
|
||||
"zh": (
|
||||
"你叫kilostar，是一个多智能体AI助手系统中的【控制节点 (Control Node)】。\n"
|
||||
"你是系统的'执行者'和'车间主任'，专门负责执行工作流中分配给你的具体子任务。\n"
|
||||
"你的工作职责是：\n"
|
||||
"1. 仔细分析分配给你的工作流步骤 (workflow_step) 的目标和要求。\n"
|
||||
"2. 运用你被分配的工具 (如有) 或者依靠自身的知识和推理能力，精准、高效地完成该任务。\n"
|
||||
"3. 将执行的结果、产生的数据或者具体的输出，严格按照 ForWorkflow 格式返回。\n"
|
||||
"请注意：你的输出应当具体、实用，直接提供任务所要求的结果，不要做过多无关的寒暄。"
|
||||
),
|
||||
"en": (
|
||||
"You are kilostar, the [Control Node] in a multi-agent AI assistant system.\n"
|
||||
"You are the system's 'executor' and 'shop floor manager', specifically responsible for carrying out concrete subtasks assigned to you within the workflow.\n"
|
||||
"Your duties are:\n"
|
||||
"1. Carefully analyze the objectives and requirements of the workflow_step assigned to you.\n"
|
||||
"2. Use the tools assigned to you (if any) or rely on your own knowledge and reasoning to complete the task accurately and efficiently.\n"
|
||||
"3. Return the execution results, generated data, or concrete outputs strictly in the ForWorkflow format.\n"
|
||||
"Note: Your output should be specific, practical, and directly provide the results requested by the task. Avoid excessive irrelevant pleasantries."
|
||||
),
|
||||
},
|
||||
}
|
||||
|
||||
# ─── API / 通用消息 ────────────────────────────────────────────────────────
|
||||
|
||||
_MESSAGES: Dict[str, Dict[str, str]] = {
|
||||
@@ -158,7 +70,6 @@ def _resolve_locale(locale: str | None = None, accept_language: str | None = Non
|
||||
if locale:
|
||||
return locale if locale in ("zh", "en") else _DEFAULT_LOCALE
|
||||
if accept_language:
|
||||
# 简单解析：取第一个 segment，若含 zh 则 zh，含 en 则 en
|
||||
first = accept_language.split(",")[0].split(";")[0].strip().lower()
|
||||
if "zh" in first:
|
||||
return "zh"
|
||||
@@ -182,26 +93,3 @@ def t(key: str, locale: str | None = None, accept_language: str | None = None, *
|
||||
loc = _resolve_locale(locale, accept_language)
|
||||
text = _MESSAGES.get(loc, {}).get(key) or _MESSAGES.get(_DEFAULT_LOCALE, {}).get(key) or key
|
||||
return text.format(**kwargs) if kwargs else text
|
||||
|
||||
|
||||
def agent_prompt(
|
||||
agent_name: str,
|
||||
locale: str | None = None,
|
||||
accept_language: str | None = None,
|
||||
custom_system_prompt: str | None = None,
|
||||
) -> str:
|
||||
"""获取指定 Agent 的 system prompt，并追加语言指令。
|
||||
|
||||
若 ``custom_system_prompt`` 不为空，追加在默认 prompt 和语言指令之后，
|
||||
使管理员自定义内容能够覆盖/补充默认行为，同时保留角色定义。
|
||||
"""
|
||||
loc = _resolve_locale(locale, accept_language)
|
||||
prompt = _PROMPTS.get(agent_name, {}).get(loc) or _PROMPTS.get(agent_name, {}).get(_DEFAULT_LOCALE, "")
|
||||
lang_instruction = {
|
||||
"zh": "\n\n【重要】请始终使用简体中文进行思考和回复。",
|
||||
"en": "\n\n[Important] Please always think and reply in English.",
|
||||
}.get(loc, "")
|
||||
result = prompt + lang_instruction
|
||||
if custom_system_prompt and custom_system_prompt.strip():
|
||||
result += f"\n\n{custom_system_prompt.strip()}"
|
||||
return result
|
||||
|
||||
Reference in New Issue
Block a user