-
…en costs across agents
-
- Updated `GET /api/agent/:agentId/info` to include heartbeat and cron configurations. - Added `PUT /api/agent/:agentId/heartbeat` to update config.json and toggle service heartbeat on the fly. - Added `PUT /api/agent/:agentId/cron` to update cron.json list. - Updated AgentChat.vue detail panel UI to include interactive heartbeat toggles and a cron job management list.
-
- Updated `POST /api/company/create` to create an empty shell without bootstrapping CXO/HR automatically. - Updated `master/agent.md` instructions so Master Agent handles all Template library hirings. - Renamed 'MasterBot' navigation link to 'System Agents'. - Updated AgentChat sidebar to only show System Agents when accessed via the System Agents link.
-
Copy innovator pipeline agents from templates/ to system/agents/: - agent-creator: scaffolds new agents - innovator: orchestrates FDE training pipeline - hunter: knowledge hunting (L3-Hunt) - digester: knowledge digestion (L2-Digest) - evolver: skill evolution (Evolving) All 6 system agents now visible in MasterBot agent list.
-
- GET /api/company/templates/:id/logs scans system agent conversations - Logs stored in system agents (agent-creator/innovator), NOT in template dir - Template directories stay clean for copying - Collapsible log cards with status, time, message count, and output summary - Auto-poll during generate/train actions (10s/15s intervals)
-
- POST /api/company/templates: scaffold new template via AgentScaffold - POST /api/company/templates/:id/generate: trigger agent-creator to write definitions - POST /api/company/templates/:id/train: trigger innovator FDE training pipeline - PUT /api/company/templates/:id/files/content: save template file content - TemplateAgents.vue: create form, action buttons, editable preview, status banner
-
- Chat list: added 🗑 delete button per conversation (hover to reveal) - Calls DELETE /api/agent/:agentId/conversations/:convId - Backend also cleans up associated log files - Detail file tree: added 🗑 delete button per file/folder (hover to reveal) - Backend: DELETE /api/agent/:agentId/file/* with path traversal protection - Detail preview: upgraded from readonly <pre> to editable <textarea> - Backend: PUT /api/agent/:agentId/file/* for saving - Shows 'unsaved' badge + save/reset buttons when dirty - Tab key support, monospace font, auto-fill height
-
- CompanyDashboard Goals Tab: upgraded from flat list to full OKR tree view with progress bars, node hierarchy, status animations, owner/priority badges - ClaudeCliProtocol: added --effort flag support (low=disable thinking) - agent-chat.js: per-agent effort config from config.json cli.effort - .gitignore: exclude data/companies/, apiconversation/, agent memory/tasks - New views: TemplateAgents, JobsPanel, PipelineEditor, SkillsMarket - docs/architecture-v5.md: added decision #13 (thinking control)
-
1. 根治所有模板 Agent残留的过往公司(LemonV)私人记忆,使其诞生即为全新白纸状态。 2. 提取出统一的 `methodology.md` 基类 Prompt,通过 `agent-chat.js` 强力注入。 3. 从 Master 到各路 Agent 都将强制遵循【从大脑到小脑】的不硬编码理念。 4. 全面引入统一的基础方法论(Harness):学习(Research) -> 规划(Planning) -> 执行(Execute) -> 验证(Verify)
-
- 移除了 master/agent.md 中关于自动部署 CEO/CTO/COO/HR 的错误硬编码约定 - 更新了 master/tools.md 工作流,明确 Master 第一步需手动 hire CEO 并派发战略指令 - 清理了 templates/ceo 下自带的、绑定具体公司的 plan.md 和 todo.md 假数据模板,确保 CEO 诞生时是一张白纸
-
核心发现:当底层 API (如 MiniMax) 发生 429 时,Claude CLI 内部会自动开启一段漫长的 exponential backoff 重试逻辑(期间完全静默,耗时可达 3 分钟之久)。 如果最终依然失败,它会抛出一个合法的 JSON 格式的 `type: "result"` 报文,此时 `is_error: true`。 旧版本会将这个 result 报文当做正常的 Agent 文本流式处理,导致把错误输出混进正常消息里。 新版本增加逻辑,在解析到 result 且 is_error 为 true 时,不进行正常 resolve,而是立即 reject Promise 抛给上层,中断一切任务并给前台报红。
-
修复 Claude CLI 遇到严重 API 错误 (如 Http 429) 时,输出的不是合法 JSON,而是像 'MiniMax 检查失败: HTTP 429: {...}' 这样的纯文本行。 旧版本在 JSON.parse 失败后直接忽略。 新版本增加 fallback,匹配非 JSON 行中的错误关键字并强制中断死等和前端展示。 -
- 当底层模型 (MiniMax等) 抛出 API 错误时,Claude CLI 不会崩溃也不会输出 stderr,而是通过 stdout 输出 event.type='error' 的 JSON 块。 - 未处理该事件导致协议层无法等到 result 事件,引发 Promise 永久挂起。 - 修复:在_handleStreamEvent 拦截 error 块,主动抛出错误打断等待链,前端即可正常展示 ❌ API 请求失败。
-
Claude CLI 遇到 API rate limit/hang 时可能既不输出 stdout 也不输出 stderr, 导致 sendPrompt Promise 永远挂起,前端卡在思考中状态。 - 新增 120s 空闲超时:无 stdout 活动自动 reject - 有 stdout 活动时重置计时器(避免长任务误判) - result 到达时清理计时器
-
- ClaudeCliProtocol: stderr 检测 rate_limit/429/401 等致命错误时自动 reject sendPrompt Promise - agent-chat.js: 监听 stderr/disconnected 事件并通过 SSE 推送到前端 - AgentChat.vue: error 事件停止 thinking 状态 + ACP 日志面板显示错误
-
- System agents: 只保留 master (data/system/agents/master) - Templates: 所有可复用 agent 模板 (data/system/templates/) - Companies: 公司创建时自动部署 5 个元 Agent (innovator/hunter/digester/evolver/agent-creator) 路径修复: - agent-chat.js: /list 扫描路径修正 (system/agents + companies/*/agents) - agent-manager.js: 动态 agent 查找路径修正 - skill-config-loader.js: 修正 agents root - pipeline-service.js: pipelines 输出到 companies/{id}/pipelines/ - billing.log: 移至 companies/{id}/logs/ 下 Skills 标准化: - 所有 template agent 建立 .claude/skills/main_skill/SKILL.md - company-service._copyTemplate() 新增 .claude/ 目录复制 - innovator SKILL.md v3.0: 移除旧 l3-hunt/l2-digest 命名 - 清理重复 agent_creator, 统一为 agent-creator 清理: - 移除 data/agents, data/workspace, data/logs, data/goals 旧目录 - 清除所有未使用的 DATA_DIR 声明 - 清除 template 中的 conversations/logs/memory 运行态数据 -
scripts/demo-harness-company.js creates a company, hires a Base Agent worker, and simulates the full RPEV lifecycle with real API calls: - Company creation (skipBootstrap) - Agent hiring with base template - meta-research initial skill mount - 3 transition API calls (plan → execute → verify) - Hot Swap verification at each stage - Artifact production validation
-
scripts/test-harness.js covers: - Meta-Skill file existence & content - Base Agent template completeness - Hot Swap simulation - Context Flush simulation - _lessons.md injection - billing.log format - GoalsService new statuses - CLI registration - Transition API route verification - Optional --online mode for live API tests
-
The plugin bootstrap was calling resolveOpenclawDist() synchronously at module load time, which crashed the entire server if the optional @mas/openclaw-dist package wasn't installed. Now all three call sites defer resolution to runtime with try/catch graceful fallback.
-
- Add task transition CLI and API for Context Flush & Hot Swap - Enforce strict bash-only tool policy for Base Agents - Inject into system prompt for self-retrying loop - Implement Goal node updates on transitions - Add P0 Execute pre-approval block (Human-in-the-loop) - Track token metrics to billing.log
-
文档更新: - 重写 11-directory-structure.md (data/system/ + data/{companyId}/) - 重写 13-api-design.md (100+ 实际 API 端点) - 更新 24-company-layer-architecture.md (规划中→已实现, Todo 全标完成) - 更新 23-agent-active-heartbeat.md (规划中→已完成) - 更新 architecture-v5.md (v5.3, Phase 4-6 新增) - 更新 21-fde-pipeline-architecture.md (阈值 90→95, 路径修正) - 更新 LEMONBOSS-SYSTEM-DESIGN.md (v2.0, 章节 15-26 索引) - 新增 25-bootstrap-mechanism.md (公司自举机制) - 新增 26-automated-hiring-orchestration.md (全自动招聘编排) Bug 修复: - fix(server): 修复 body sanitizer 空 body 时未设置 _bodyParsed 导致 express.json() 重复读取已消费流的 stream-not-readable 错误 -
核心改动: 1. agent-chat.js buildSystemPrompt 新增 Layer 0: 为公司Agent自动注入 公司环境上下文(companyId、roleName、公司共享工作区路径) 明确禁止写入全局 workspace/ 或 data/workspace/ 2. CEO 模板更新: workspace/ 引用改为"公司共享工作区" 3. 清理旧的 workspace/ 和 data/workspace/ 下的废弃公司目录
-
这些目录是Agent执行任务时误写到全局agents目录下的, 公司Agent的正确路径应为 data/<companyId>/agents/<role>/
-
核心改动: 1. agent.md: 公司创建流程从5步手动操作改为1条命令自动完成 2. agent.md: 新增自主决策规则 — 用户不给ID时自己起名立刻执行,禁止追问 3. agent.md: 管辖实体从 agent-creator 更新为各公司 HR 4. agent.md: 新增完整的 Bootstrap 自动流水线图示 5. tools.md: 新增 company templates / company fire CLI 文档 6. tools.md: company create 标注为自动Bootstrap
-
Phase A - Company Bootstrap 自举: - 新增 _company_bootstrap/manifest.json 模板 - company create 时自动部署 CEO/CTO/COO/HR 四名核心骨干 - 自动启动公司 + 2s后向CEO dispatch战略启动令 - 支持 skipBootstrap 参数跳过自举 Phase B - HR 大一统 (招留管退): - 新增 hr 模板(agent_creator 的进化体) - HR 具备完整生命周期管理:招聘/技能装配/监控/辞退 - HR 具备模板发现能力(lemon company templates 查看可用模板如 scrapling_crawler) - CTO 模板重写:不再亲自 hire,全部通过 task dispatch 向 HR 下发招聘需求单 - CEO 模板更新:确认 Bootstrap 已部署骨干,委派时强调 CTO→HR 招聘链 - 新增 POST /company/:id/fire API(停心跳→归档→更新名单) - 新增 CLI: lemon company fire / lemon company templates