agent-contracts-backend-runtime

Estrellas12

Forks0

Actualizado17 de enero de 2026 a las 10:31

Build an API-oriented agent using AgentRuntime/StreamingRuntime with predictable request/response slices and session support.

Instalación

Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.

Fuente

yatarousan0227

yatarousan0227/agent-contracts

Abrir repositorio de GitHub Ver repositorios del creador

Descarga

Ocupaciones relacionadasSOC

Basado en la clasificación ocupacional SOC

Desarrolladores de softwareOcupaciones informáticas y matemáticas·SOC 15-1252

Explorador de archivos

4 archivos

SKILL.md

readonly

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"}

agent-contracts Backend Runtime

Use this skill when you are implementing an AI agent as a backend service (HTTP API, jobs, or SSE streaming).

Target Shape

Input: RequestContext(session_id, action, params, message, image, resume_session)
Output: response.response_type + response.response_data (+ optional response.response_message)
State slices: request, response, _internal + domain slices (e.g., ticket, orders, workflow)

Recommended Workflow

Start from examples/05_backend_runtime.py.
Define your domain slices and register them: NodeRegistry.add_valid_slice("your_slice").
Implement nodes with NodeContract (keep reads/writes minimal).
Build graph with build_graph_from_registry(...) and compile.
Wrap with AgentRuntime for request/response execution.
If you need progressive updates, use StreamingRuntime and emit SSE via StreamEvent.to_sse().

Guardrails

Prefer response.response_type for flow termination and client branching.
Avoid writing to request (discouraged).
Keep large blobs out of state slices; sanitize before LLM routing (see GenericSupervisor).

References (load only when needed)

docs/getting_started.md
docs/core_concepts.md
docs/cli.md
docs/skills/official/agent-contracts-backend-runtime/references/patterns.md

Más de este repositorio

mismo repositorio

agent-contracts-app-builder

yatarousan0227/agent-contracts

Build a production-minded AI agent using agent-contracts (contracts, slices, validation, graph, runtime, CLI tooling).

2026-01-1712

agent-contracts-contracts-ci

yatarousan0227/agent-contracts

Make contract-driven agents safe to change with strict validation, architecture docs, and contract diffs in CI.

2026-01-1712

agent-contracts-interactive-flow

yatarousan0227/agent-contracts

Build question/answer style agents using InteractiveNode, explicit routing, and workflow slices.

2026-01-1712

agent-contracts-routing-tuning

yatarousan0227/agent-contracts

Tune routing with TriggerCondition priorities, LLM hints, context_builder, and traceable decisions.

2026-01-1712

agent-contracts-tool-use-rag

yatarousan0227/agent-contracts

Implement tool-using or retrieval-style nodes with services, dependency injection, and safe LLM context building.

2026-01-1712

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"}

agent-contracts Backend Runtime

Use this skill when you are implementing an AI agent as a backend service (HTTP API, jobs, or SSE streaming).

Target Shape

Input: RequestContext(session_id, action, params, message, image, resume_session)
Output: response.response_type + response.response_data (+ optional response.response_message)
State slices: request, response, _internal + domain slices (e.g., ticket, orders, workflow)

Recommended Workflow

Start from examples/05_backend_runtime.py.
Define your domain slices and register them: NodeRegistry.add_valid_slice("your_slice").
Implement nodes with NodeContract (keep reads/writes minimal).
Build graph with build_graph_from_registry(...) and compile.
Wrap with AgentRuntime for request/response execution.
If you need progressive updates, use StreamingRuntime and emit SSE via StreamEvent.to_sse().

Guardrails

Prefer response.response_type for flow termination and client branching.
Avoid writing to request (discouraged).
Keep large blobs out of state slices; sanitize before LLM routing (see GenericSupervisor).

References (load only when needed)

docs/getting_started.md
docs/core_concepts.md
docs/cli.md
docs/skills/official/agent-contracts-backend-runtime/references/patterns.md