Menu
Build an API-oriented agent using AgentRuntime/StreamingRuntime with predictable request/response slices and session support.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Build a production-minded AI agent using agent-contracts (contracts, slices, validation, graph, runtime, CLI tooling).
Make contract-driven agents safe to change with strict validation, architecture docs, and contract diffs in CI.
Build question/answer style agents using InteractiveNode, explicit routing, and workflow slices.
Tune routing with TriggerCondition priorities, LLM hints, context_builder, and traceable decisions.
Implement tool-using or retrieval-style nodes with services, dependency injection, and safe LLM context building.
| name | agent-contracts-backend-runtime |
| description | Build an API-oriented agent using AgentRuntime/StreamingRuntime with predictable request/response slices and session support. |
| metadata | {"short-description":"Backend runtime patterns"} |
Use this skill when you are implementing an AI agent as a backend service (HTTP API, jobs, or SSE streaming).
RequestContext(session_id, action, params, message, image, resume_session)response.response_type + response.response_data (+ optional response.response_message)request, response, _internal + domain slices (e.g., ticket, orders, workflow)examples/05_backend_runtime.py.NodeRegistry.add_valid_slice("your_slice").NodeContract (keep reads/writes minimal).build_graph_from_registry(...) and compile.AgentRuntime for request/response execution.StreamingRuntime and emit SSE via StreamEvent.to_sse().response.response_type for flow termination and client branching.request (discouraged).GenericSupervisor).docs/getting_started.mddocs/core_concepts.mddocs/cli.mddocs/skills/official/agent-contracts-backend-runtime/references/patterns.md