superagent-base

Eino ADK WrapInvokableToolCall middleware pattern for intercepting all tool calls. TRIGGER when: implementing tool-level middleware (sandbox, logging, auth, metrics) in this project's Eino ADK agents. DO NOT TRIGGER when: working with agent-level middleware (timeout, retry) or non-Eino tool systems.

Reference for the A2UI SSE streaming protocol used by Superagent agents to push typed events to the frontend. TRIGGER when: implementing a new event type, debugging streaming output, writing frontend SSE consumers, or when the user asks "how does streaming work", "what events does the agent emit", "A2UI 协议". DO NOT TRIGGER when: working on HTTP REST endpoints unrelated to streaming.

Author and validate Superagent declarative YAML agent definitions (apiVersion: superagent/v1, kind: Agent). TRIGGER when: creating a new agent, editing configs/agents/*.yaml, reviewing agent spec fields, or when the user asks "how do I define an agent", "write me an agent yaml", "agent 配置怎么写". DO NOT TRIGGER when: working on workflow DAG nodes (use workflow-dag skill), pure Go backend logic, or infrastructure config.

Analyzes code errors, generates fix solutions, evaluates and applies fixes. Use when fixing test failures, compilation errors, runtime exceptions, "编码修复", "code fix", "fix this error", or when the user asks to debug and fix code issues.

Implement and debug agent interrupt/resume (human-in-the-loop checkpointing) in Superagent. TRIGGER when: enabling interrupt on an agent, implementing resume API, debugging "checkpoint not found" errors, adding human approval steps, or when the user asks "interrupt/resume 怎么用", "how does checkpoint work", "pause agent for approval". DO NOT TRIGGER when: building non-interactive batch agents or simple one-shot queries.

Patterns for integrating MCP (Model Context Protocol) servers and tools into Superagent agents. TRIGGER when: wiring an MCP server into an agent YAML, implementing a new MCP client/server, debugging "mcp tool not found" errors, or when the user asks "how do I add an MCP tool", "MCP 怎么接入", "connect filesystem MCP". DO NOT TRIGGER when: writing pure builtin tools (use builtin/<name> directly) or REST API integrations unrelated to MCP.

Guide for configuring and debugging the model routing layer in Superagent. TRIGGER when: adding a new model provider, configuring fallback chains, tuning cost/latency routing strategy, debugging "model not found" errors, or when the user asks "how does model routing work", "模型路由怎么配置", "add a new LLM provider". DO NOT TRIGGER when: writing agent YAML (use agent-yaml-authoring), implementing tool logic, or working on the UI.

Design multi-agent systems using Superagent's supervisor, sequential, and parallel agent types. TRIGGER when: building orchestration agents, routing tasks between sub-agents, designing fan-out/fan-in pipelines, or when the user asks "multi-agent 怎么设计", "supervisor agent", "parallel agents", "agent orchestration". DO NOT TRIGGER when: working on single-model agents (use agent-yaml-authoring) or workflow DAG nodes (use workflow-dag skill).

Set up and query Superagent's observability stack: OpenTelemetry traces, Prometheus metrics, and Grafana dashboards. TRIGGER when: debugging latency or errors via traces, adding custom metrics, configuring OTel collector, reading Grafana dashboards, or when the user asks "如何查看 trace", "metrics 怎么看", "observability 怎么接入", "add a span to my code". DO NOT TRIGGER when: working on agent logic, model routing, or frontend UI.

Configure and extend the tool middleware chain (retry, timeout, rate-limit, cache) in Superagent. TRIGGER when: adding retry logic to a tool, configuring per-tool timeouts, implementing tool response caching, debugging "tool timeout" errors, or when the user asks "how do I add retry to a tool", "工具超时怎么设置", "tool middleware". DO NOT TRIGGER when: implementing the tool's core logic or writing MCP servers.

Design and debug Superagent workflow DAG agents (type: workflow). TRIGGER when: designing a multi-step workflow, connecting DAG nodes, handling branch/condition logic, or when the user asks "how does workflow execution work", "DAG 怎么定义", "add a conditional branch to my workflow". DO NOT TRIGGER when: building single-model agents (use agent-yaml-authoring), orchestration with supervisor/sequential types, or simple tool-calling agents.