Canonical support matrix

What “supported” means in Once

Once uses several different integration layers. This page separates them so “supported” is not mistaken for a universal runtime guarantee.

Key: “Example” means public integration guidance exists. “Hostile-retry evidence” means a reproducible failure lab exists. “Discovery” means Once can inspect or classify the tool surface. “Protected runtime path” means the Once execution boundary is actually on the path of the side effect.

Framework / host	Integration example	Hostile-retry evidence	Discovery / classification	Protected runtime path
OpenAI Agents	Yes	No dedicated hostile-retry lab claimed here	Yes — FunctionTool structural wrapping / Connect path	Yes, when tools are routed through the supported Once local or hosted execution boundary
Vercel AI SDK	Yes	No dedicated hostile-retry lab claimed here	Yes — documented discovery support	Yes, when the consequential tool is routed through a supported Once boundary
LangChain / LangGraph	Yes	Yes — LangGraph hard-process-death / fresh-process recovery lab	Yes — documented discovery support	Yes, for the tested / integrated path
CrewAI	Yes	Yes — native BaseTool hostile-retry lab	Runtime discovery adapter not claimed as equivalent to protection	Yes, for the tested / integrated path
Microsoft Agent Framework	Yes	No dedicated hostile-retry lab claimed here	Framework integration documented	Yes, when routed through a supported Once boundary
Agno	Evidence-focused example	Yes — retries after successful tool execution followed by model HTTP 500	Do not infer discovery-adapter support from the hostile-retry lab	Yes, for the released SDK path used by the lab
Claude Code	MCP / plugin setup	Not a framework hostile-retry benchmark	MCP-assisted assessment and setup	MCP installation alone is not protection; runtime must sit on the side-effect path
Cursor	Project-scoped MCP setup	Not a framework hostile-retry benchmark	MCP-assisted assessment and setup	MCP installation alone is not protection
Codex	Plugin / marketplace setup	Not a framework hostile-retry benchmark	Plugin teaches routing / assessment and exposes MCP	Plugin installation alone is not the runtime safety boundary

Current automatic local protection boundary

@once-agent/sdk/connect can classify supported local tool descriptors as BYPASS, PROTECT, or fail-closed UNKNOWN, resolve trusted logical identity, bind effect-bearing data, and connect supported same-machine tool registries. Automatic protected local execution uses durable same-machine SQLite on Node.js 24.15+.

This is not a multi-host or universal exactly-once guarantee. A framework being listed here does not mean every tool, provider, transport, HTTP method, or deployment topology is automatically protected.

Evidence boundary

The strongest public framework-specific duplicate-effect evidence currently comes from the LangGraph, CrewAI, and Agno hostile-retry labs. Other entries may be integration examples or discovery support rather than equivalent crash-test evidence.

Project identity · Provider reconciliation matrix · Research · GitHub