GoClaw/todo.md

GoClaw Control Center TODO

• Basic Dashboard layout (Mission Control theme)
• Agents page with mock data
• Nodes page with mock data
• Chat page with mock conversation
• Settings page with provider cards
• Docker Stack integration
• Fix Home.tsx conflict after upgrade
• Fix DashboardLayout.tsx conflict after upgrade
• Create server-side Ollama API proxy routes (tRPC)
• Integrate real Ollama /v1/models endpoint in Settings
• Integrate real Ollama /v1/chat/completions in Chat page
• Add OLLAMA_API_KEY and OLLAMA_BASE_URL secrets
• Write vitest tests for Ollama API proxy
• Update Dashboard with real model data
• Add streaming support for chat responses
• Connect real Docker Swarm API for node monitoring
• Add authentication/login protection

Phase 1: Agent Management UI

• Connect Agents page to trpc.agents.list (load real agents from DB)
• Create AgentDetailModal component for viewing agent config
• Create AgentCreateModal component with form validation
• Implement agent update mutation (model, temperature, maxTokens, systemPrompt)
• Implement agent delete mutation with confirmation
• Add start/pause/restart actions for agents
• Add agent metrics chart (requests, tokens, processing time)
• Add agent history view (recent requests/responses)
• Write vitest tests for agent management components

Phase 2: Tool Binding System

• Design Tool Binding API schema
• Create tool registry in database
• Implement tool execution sandbox
• Add tool access control per agent
• Create UI for tool management

Phase 3: Tool Integration

• Implement Browser tool (HTTP fetch-based)
• Implement Shell tool (bash execution with safety checks)
• Implement File tool (read/write with path restrictions)
• Implement Docker tool (container management)
• Implement HTTP tool (GET/POST with domain whitelist)

Phase 4: Metrics & History

• AgentMetrics page with request timeline chart
• Conversation history log per agent
• Raw metrics table with token/time data
• Stats cards (total requests, success rate, avg response time, tokens)
• Time range selector (6h/24h/48h/7d)
• Metrics button on agent cards
• Navigation: /agents/:id/metrics route
• Tools page added to sidebar navigation

Phase 5: Specialized Agents

Browser Agent

• Install puppeteer-core + chromium dependencies
• Create server/browser-agent.ts — Puppeteer session manager
• tRPC routes: browser.start, browser.navigate, browser.screenshot, browser.click, browser.type, browser.extract, browser.close
• BrowserAgent.tsx page — live browser control UI with screenshot preview
• Session management: multiple concurrent browser sessions per agent
• Add browser_agent to agents DB as pre-seeded entry

Tool Builder Agent

• Create server/tool-builder.ts — LLM-powered tool generator
• tRPC routes: toolBuilder.generate, toolBuilder.validate, toolBuilder.install
• Dynamic tool registration: add generated tools to TOOL_REGISTRY at runtime
• Persist custom tools to DB (tool_definitions table)
• ToolBuilder.tsx page — describe tool → preview code → install
• Add tool_builder_agent to agents DB as pre-seeded entry

Agent Compiler

• Create server/agent-compiler.ts — LLM-powered agent factory
• tRPC routes: agentCompiler.compile, agentCompiler.preview, agentCompiler.deploy
• AgentCompiler.tsx page — ТЗ input → agent config preview → deploy
• Auto-populate: model, role, systemPrompt, allowedTools from ТЗ
• Add agent_compiler to agents DB as pre-seeded entry

Integration

• Add all 3 pages to sidebar navigation
• Write vitest tests for all new server modules
• Push to Gitea (NW)

Phase 6: Agents as Real Chat Entities

• Remove unused pages: BrowserAgent.tsx, ToolBuilder.tsx, AgentCompiler.tsx
• Seed 3 agents into DB: Browser Agent, Tool Builder Agent, Agent Compiler
• Add tRPC chat endpoint: agents.chat (LLM + tool execution per agent)
• Update Chat UI to support agent selection dropdown
• Create /skills page — skills registry with install/uninstall
• Update /agents to show seeded agents with Chat button
• Update /tools to show tools per agent with filter by agent
• Add /skills to sidebar navigation
• Write tests for chat and skills endpoints

Phase 6: Orchestrator Agent (Main Chat)

• Fix TS errors: browserSessions/toolDefinitions schema exports, z.record
• Seed 3 specialized agents into DB (Browser, Tool Builder, Agent Compiler)
• Create server/orchestrator.ts — main orchestrator with tool-use loop
• Orchestrator tools: shell_exec, file_read, file_write, http_request, delegate_to_agent, list_agents, list_skills, install_skill
• Add trpc.orchestrator.chat mutation (multi-step tool-use loop with LLM)
• Update /chat UI: show tool call steps, agent delegation, streaming response
• Create /skills page with skill registry (install/remove/describe)
• Add /skills to sidebar navigation
• Update /agents to show seeded agents with Chat button
• Write tests for orchestrator

Phase 7: Orchestrator as Configurable System Agent

• Add isSystem + isOrchestrator fields to agents table (DB migration)
• Seed Orchestrator as system agent in DB (role=orchestrator, isSystem=true)
• Update orchestrator.ts to load model/systemPrompt/allowedTools from DB
• Update /chat to read orchestrator config from DB, show active model in header
• Update /agents to show Orchestrator with SYSTEM badge, Configure button, no delete
• AgentDetailModal: orchestrator gets extra tab with system tools (shell, docker, agents mgmt)
• Add system tools to orchestrator: docker_ps, docker_restart, manage_agents, read_logs
• /chat header: show current model name + link to Configure Orchestrator

Phase 8: Fix Orchestrator Chat

• Fix: orchestrator uses model from DB config (minimax-m2.7, not hardcoded fallback)
• Fix: real tool-use loop — execute shell_exec, file_read, file_list tools
• Fix: show tool call steps in Chat UI (tool name, args, result, duration)
• Fix: Chat.tsx shows which model is being used from orchestrator config
• Fix: Streamdown markdown rendering for assistant responses
• Add: streaming/SSE for real-time response display

Phase 9: Go Gateway Migration (Variant C)

• Create gateway/ directory with Go module (git.softuniq.eu/UniqAI/GoClaw/gateway)
• Implement config/config.go — env-based configuration
• Implement internal/llm/client.go — Ollama API client (chat, models, health)
• Implement internal/db/db.go — MySQL connection, agent/config queries
• Implement internal/tools/executor.go — Tool Executor (shell_exec, file_read, file_write, file_list, http_request, docker_exec, list_agents)
• Implement internal/orchestrator/orchestrator.go — LLM tool-use loop, config from DB
• Implement internal/api/handlers.go — REST API handlers
• Implement cmd/gateway/main.go — HTTP server with chi router, graceful shutdown
• Go Gateway compiles successfully (10.8MB binary)
• Create server/gateway-proxy.ts — Node.js proxy client to Go Gateway
• Create docker/docker-compose.yml — local dev (control-center + gateway + ollama + db)
• Create docker/docker-stack.yml — Docker Swarm production (2 replicas, rolling updates)
• Create docker/Dockerfile.gateway — multi-stage Go build
• Create docker/Dockerfile.control-center — multi-stage Node.js build
• Update server/routers.ts: replace orchestrator.ts calls with gateway-proxy.ts calls
• Write Go unit tests (gateway/internal/tools/executor_test.go)
• Write Go integration test for orchestrator chat loop
• Push to Gitea (NW)

Phase 10: LLM Provider Configuration

• config.go: default LLM_BASE_URL = https://ollama.com/v1 (Ollama Cloud)
• config.go: support LLM_BASE_URL + LLM_API_KEY env vars (legacy OLLAMA_* aliases kept)
• config.go: normaliseLLMURL() — auto-append /v1 for bare Ollama hosts
• docker-compose.yml: ollama service commented out (GPU only), LLM_BASE_URL/LLM_API_KEY added
• docker-stack.yml: ollama service commented out (GPU only), llm-api-key secret added
• docker/.env.example: 4 LLM provider options documented (Ollama Cloud, OpenAI, Groq, Local GPU)