Research sources

Agent Runtime v0.1 was informed by current standards and implementation patterns. These sources are references, not dependencies.

Standards and protocols

• Model Context Protocol specification: tools, resources, prompts, sampling, roots, JSON-RPC message shape, and capability negotiation.
• Agent2Agent Protocol specification: agent cards, peer tasks, messages, artifacts, streaming, push notifications, security, and protocol bindings for agent-to-agent interoperability.
• Google Developers Blog: Announcing the Agent2Agent Protocol: original A2A positioning around capability discovery, task management, artifacts, collaboration, existing web standards, and MCP complementarity.
• Linux Foundation A2A project announcement: project governance and vendor-neutral direction for A2A as an open agent-to-agent communication protocol.
• A2A GitHub project: released specification, protocol assets, SDKs, samples, and issue history.
• CloudEvents specification: portable event envelope concepts such as event type, source, id, time, subject, content type, and extension attributes.
• JSON-RPC 2.0 specification: request, response, notification, method, params, result, and error semantics for transport-neutral control planes.
• OpenTelemetry concepts: traces, spans, logs, metrics, context propagation, baggage, and service/resource attribution.
• W3C Trace Context: traceparent and tracestate propagation across services.
• AsyncAPI specification: event-driven API description patterns.

Provider and framework references

• OpenAI API streaming reference: provider stream events such as response lifecycle, text deltas, and output item updates.
• Anthropic Messages streaming: message start, content block start/delta/stop, message delta, and message stop event structure.
• Anthropic tool use: tool use and tool result blocks as explicit content, not prose-only execution.
• Vercel AI SDK: streamText, generateObject, tool calls, tool results, steps, stop conditions, and typed UI messages.
• LangGraph durable execution: persistence, checkpoints, threads, human-in-the-loop, and time-travel patterns for long-running agents.
• LangGraph interrupts and streaming: checkpointer-backed interrupts, resume commands, thread ids, and task-mode streaming.
• OpenAI Agents SDK: agents, handoffs, sessions, guardrails, tracing spans, and streaming events for multi-agent workflows.
• Temporal workflows: workflow ids, run ids, task queues, activities, child workflows, signals, cancellation, retry policies, history, and durable execution.

Design conclusions

• Runtime events should use a stable envelope, but not require one transport.
• Provider streams should be adapted instead of exposed directly as the portable contract.
• Tool calls and human approvals need explicit ids and lifecycle records.
• Durable snapshots are required because event streams alone do not solve old sessions or process restart.
• Observability correlation belongs in the runtime contract, not only in logs.
• Agent-to-agent work should be modeled as local tasks, subagents, jobs, or remote task refs with parent links; A2A is the peer interoperability reference, not a replacement for runtime facts.
• Task lifecycle must be separate from todo/checklist state and preserve attempts, dependencies, waiting reasons, and delivery state.
• A2A messages and artifacts support the same separation used by Agent Runtime: communication belongs in messages or channel events, while durable outputs belong in artifact refs linked to tasks.