-
远程部署前置需求:登录鉴权 + 公司级多租户隔离。后端 auth.js/jwt-auth.js(注册/登录/ JWT-cookie/OAuth)本来就已经可用,这次只是把它接到前端。 - scripts/seed-admin-user.js(npm run seed:admin):幂等种子脚本,建出 admin/hex1234, role=admin。 - web/src/composables/useAuth.js + views/Login.vue:登录态 + 登录页。 - router/index.js 全局 beforeEach:未登录跳 /login?redirect=...,登录后带着原目标跳回。 - main.js 全局 401 拦截器:cookie 中途过期同样兜住,不止页面切换那一刻。 - AppNav.vue:显示用户名 + 退出登录。 - 顺手修:App.vue 原来无条件渲染 MasterChatDrawer,登录页也会露出这个悬浮入口, 改成登录且非登录页才显示。 业务路由还没加锁(Phase 1 的事),登录后依然能看到现状全部数据,符合这一阶段的验收边界。 真实浏览器走过一遍全部流程(跳转/登录/跳回/直接刷新受保护路由/退出),npm run build 通过。 Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
-
system/templates/ 已在 28 号文档的合并里并入 system/agents/,「模板」作为独立 数据概念已经消失;确认后手工 CRUD 页面(创建/改名/删除骨架、触发生成与训练、 传 skill 文件、provision)也已经没人用,一并下线: - 前端:删 AppNav「Templates」菜单项、/templates 路由、TemplateAgents.vue - 后端:company.js 删掉只服务于该页面的写接口(PATCH/DELETE/POST /templates、 generate/train/skills-upload/provision/files 系列),保留 GET /templates (CompanyDashboard 招聘弹窗和 CLI `company templates` 命令仍依赖它列出可招角色) - CLI:bin/lemon.js 删 `template create`/`template train`(调用的是被删接口) - 修正两处过时注释(company-service.js / graph-service.js):不再声称 buildAgentDefinitionBrief 有两个调用方,/hire 是唯一派单点 - work-layer-body-paths.test.js 同步更新断言(2 处调用方 → 1 处) Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
-
只做了这一件事,没有跟着做「dream 改成 org/work graph 来跑」——两者被 单独评估过:org/work graph 是单公司作用域(org graph=公司级 workflow, work graph=公司内某任务的节点图),dream 却是跨公司扫描,套进去要么破坏 作用域假设要么得新开图类型;且 graph 引擎自带的验收机制(goal-contract benchmark/test-script)判的是「产物过没过验收脚本」,对「经验提炼得对 不对」这种自由文本判断没有对应机制——不管套不套 graph 都得单独设计 rubric,是同一件事。用户明确只要 REST/控制台这一半。 ## REST(server/routes/dream.js,挂 /api/dream) 路由本身没有新业务逻辑,全部委托给已测过的 dream-service.js: GET /agents(总览)、GET /agents/:id(详情,含定义文件可写性 + 经验 审计)、POST /agents/:id/run(手动跑一次,dryRun 只看有没有新原料不 起 LLM)、POST /sweep + GET /sweep/status(全量扫描后台跑 + 轮询,内存 态并发锁防止连点两下)。 ## 控制台(web/src/views/DreamConsole.vue,路由 /dream) 一个表格 + 两个弹窗:本体列表(详情/跑一次/dry-run)+ 全量扫描按钮 (15 秒轮询状态)。导航栏加 🌙 Dream 入口。 ## 验证 server/tests/unit/dream-routes.test.js 4 例,monkeypatch 掉 dream-service 导出对象上的六个函数(不走真文件系统,不误扫真仓库 76 个本体),只验路由层自己的逻辑:端点接线、sweep 并发锁状态机。 真起服务器打了真数据:GET /agents/innovator-evolver 正确报 SKILL.md 因没进 git 历史而不可写、经验审计吐出上次真跑沉淀的 4 条 经验及原文;dry-run 正确报 no-new-material,没多花一次 LLM 调用。 浏览器里走了一遍列表→详情→dry-run,与直接打 API 结果一致。 955 个单测全绿。 文档:29-dream-design.md §5.7 记录实现与「为什么不做 graph 化」的 理由;28-followups.md / docs/README.md 同步更新 dream 现状。 Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
-
用 9 个并行 agent 按「文件独占」划分实现 P2 的 T1-T9(T0 已于 2255f09 完成)。 详见 docs/todo/system-design/27-p2-org-graph.md §五。 阶段 A · 数据层 - graph-db.js: org_graph_nodes 加 status/reports_to_node_id(PRAGMA 探测后 ALTER, 幂等);全量唯一索引换成 WHERE status='active' 的部分索引,使「fire 后重新 hire 同角色」可行;org_graph_edges 重建为执行流边(condition/edge_kind/status) - graph-service.js: ensureOrgGraphNodeIndex 同步改建部分索引,且 upsertOrgGraphNode 的 ON CONFLICT 必须写成 ON CONFLICT(company_id, role_name) WHERE status='active' —— SQLite 的冲突目标要与部分索引谓词逐字对应,否则整条 INSERT 直接失效 - org-graph-service.js(新): validateGraph 四项校验 + writeGraph/patchGraph/ getGraph/removeNode,事务化,节点软删除级联失效相关边 - routes/company.js: 四个端点 POST/PATCH/GET /org-graph + POST /org-graph/replan; /create 接入自动招聘 orggraph-planning + 异步触发(失败降级为空壳公司); /fire 接入节点软删除 阶段 B · 自动生成 - system/org-graph-templates/{dev,content,ops}.json + README:三张三段式骨架 (规划→执行→验收,验收失败回退到执行节点),角色名遵循 {domain}-{职能} - system/templates/orggraph-planning/:新 system agent(type='meta-bootstrap'), 含 §4.1 八步工作流 - company-service.js: 模板不存在时从 system/templates/base/ 元 agent 继承骨架 (自动带 RESEARCH→PLAN→EXECUTE→VERIFY 四段式)+ agent-creator 填充, 新建 agent scope='company'。这是 27-E2E §八bis 元 agent 继承的落地点 阶段 C · 展示 - CompanyDashboard.vue: 组织流程拓扑链渲染 + 空态降级 + 环深度保护 并行编排中发现并修复的三处(均不在原任务划分内): - AppNav.vue 建公司表单缺 goal 输入框 —— T0 只改了后端,前端表单没同步, company-goal 实际传不进来。这是上一轮 T0 的遗漏 - graph-seed-service.js 会把 type='meta-bootstrap' 的 orggraph-planning 塞回 org graph,与 hire() 的 guard 不一致 - graph-agent-p1-acceptance.test.js: hire 未知角色的返回从 needs_training 改为 hired_from_base(T5b 的行为变更),断言同步 验证(独立复核,非 agent 自述): - npm run test:unit 676 passed / 63 files(基线 652,+24 为新增的 org-graph 用例) - npm run web:build 通过 - 三个模板 JSON 实跑 validateGraph 全部通过;四类非法图各自被对应 rule 拒绝; writeGraph→getGraph→removeNode 级联验证通过(删中间节点后 3 条边全部失效) Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
-
1. Workspace page: left file tree + right detail/editor panel - File info: name, path, size, created/modified timestamps - Three view modes: Code / Preview / Edit with save - HTML files auto-open in Preview tab (sandboxed iframe) 2. Backend APIs: - GET/PUT /:companyId/workspace/files (list + content + save) - PUT /:companyId/files/content (company file save) 3. Navbar: removed Skills/Jobs/Pipeline, added Workspace 4. All nav links open in new tabs (target=_blank)
-
- Add TaskTimeline.vue: two-pane dashboard with task list + message timeline - Add task-service.js: aggregate cross-agent conversations into task tree - 4-strategy parent-child inference (explicit meta, time-overlap, conv→tpl, master→T) - Read messages.log for full tool call details (not just history.json) - Add tasks.js API routes: GET /api/tasks, GET /api/tasks/:taskId/timeline - Mount /api/tasks in agent-server.js - Add 'Task Logs' nav entry in AppNav.vue after Templates - Support taskId in URL (/tasks/:taskId?) for sharing/bookmarking - Add --parent flag to CLI task dispatch for explicit parentTaskId - Auto-detect parentTaskId in task/dispatch from sender's active task - Add --instructions flag to template train CLI command - Update master tools.md with new parameters
-
…en costs across agents
-
- 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.
-
- 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)
-
- 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
-
- Add Company Overview tab as default landing page - Show company info: status, uptime, agent count, heartbeat status - Start/Stop company buttons (activate/deactivate all agent heartbeats) - Per-agent heartbeat controls: interval dropdown, start/stop buttons - Backend APIs: GET status, POST start/shutdown, PUT/POST agent heartbeat - Track startedAt timestamp for uptime calculation - Update CEO agent.md with mandatory 5-step startup workflow - Fix company nav to default to overview tab
-
…ter Agent cognitive auto-recovery loop - Refactored CompanyDashboard into read-only Observer UI - Enforced strict companyId:roleId namespacing across Node APIs and AgentManager - Added dynamic <env_status> injection to PromptBuilder for robust context - Introduced bin/lemon.js CLI for structured LLM tool execution - Implemented in-stream error interceptors for implicit silent retry loop
-
- Implement OKR GoalsService with hierarchical node tracking - Add /api/goals routes and integrate with dispatch/report APIs - Create Innovator agent with Hunt→Digest→Evolving pipeline - Create Hunter (l3-hunt), Digester (l2-digest), Evolver (evolving) meta agents - Copy L1/L2 dependency skills into each agent's .claude/skills/ - Fix buildSystemPrompt to scan ALL skill subdirectories (critical) - Fix agent list sorting: master pinned top, rest by lastActiveAt - Rename master-001→master, innovator-001→innovator - Establish meta agent output convention: write to target agent dir - Add CXO agent base class for management agents - Update CEO agent with delegation-first management model
-
- Agent as Micro-Container: each agent lives in data/agents/{id}/ with full encapsulation - Persona vs Capability split: agent.md (identity) + .claude/skills/main_skill/SKILL.md (workflow) - Conversations co-located: data/agents/{id}/conversations/ replaces global dir - Meta Skills renamed: meta_hunt, meta_digest, meta_creator, meta_evolving, meta_benchmark, meta_research - Dynamic Hot-Reload: AgentManager.getAgentConfig() falls back to filesystem scan - Parallel Sub-Agent orchestration via Promise.all with multi-terminal UI - Removed SQLite dependency, global skills/ directory, and legacy conversations/ - Full architecture docs: 18-local-filesystem-first-agent-encapsulation.md