@ingram-tech/eve-ingram-cloud

Wire an Ingram Cloud smith into an eve agent. A thin, idiomatic extension of eve: run a smith as your agent's model, attach Ingram-hosted tools as an MCP connection, and resolve approvals — each over an industry-standard surface, no bespoke protocol.

Philosophy: stand on the standard

This package adds no proprietary client. The model rides Ingram Cloud's OpenAI-compatible API as a plain AI SDK LanguageModel (eve takes one directly); tools ride MCP through eve's own connection system; approvals ride the standard tool-call channel. A smith still runs the agent loop server-side — memory, tools, approvals, isolation — but to eve it looks like any model.

Install

npm install @ingram-tech/eve-ingram-cloud

eve and ai are peer dependencies — you already have them in an eve project.

Model: a smith as your agent's model

eve's model takes an AI SDK LanguageModel, so a smith drops straight into agent/agent.ts:

// agent/agent.ts
import { defineAgent } from "eve";
import { ingramCloudModel } from "@ingram-tech/eve-ingram-cloud";

// A per-smith token names exactly one smith; the agent is the one that smith runs.
export default defineAgent({
  model: ingramCloudModel({ apiKey: process.env.IC_SMITH_TOKEN! }),
});

eve routes this as an external provider — it bypasses the AI Gateway and talks to Ingram Cloud directly.

The model id is the LLM, not the agent

The agent a smith runs — its instructions, tools, and memory — is resolved from the smith, never from the model id. modelId is the upstream inference LLM for the turn: omit it to use the smith's configured model, or name one to override it (ingramCloudModel({ apiKey, modelId: "gpt-5.5" })).

Opt into Ingram Cloud's server-side memory with threadId. Server-side with a tenant-admin token instead of a smith token? Name the smith with smithId:

ingramCloudModel({ apiKey: process.env.IC_TENANT_TOKEN!, smithId: "smt_…" });

Never ship a tenant-admin token to the browser.

Tools: Ingram-hosted MCP as an eve connection

Expose an Ingram Cloud deployment of kind: "mcp" as an eve connection. The filename is the connection name:

// agent/connections/ingram.ts
import { defineIngramMcpConnection } from "@ingram-tech/eve-ingram-cloud";

export default defineIngramMcpConnection({
  apiKey: process.env.IC_SMITH_TOKEN!,
  deploymentId: "dep_…",
  description: "Ingram-hosted tools for this smith.",
});

eve discovers the deployment's tools, brokers auth, and hands them to the model — the token never reaches the model. Gate them with eve's own per-connection approval (never() / once() / always() from eve/tools/approval) or filter with tools: { allow: [...] }.

This is distinct from ingramCloudModel: there a smith runs its own server-side tools as the model; here an eve agent calls Ingram-hosted tools directly over MCP.

Approvals (human-in-the-loop)

A smith tool marked destructiveHint pauses its run for approval. On the OpenAI-compatible surface the pause arrives as a tool call whose id is "<run_id>::<tool_call_id>" and the turn ends with finish_reason: "tool_calls". The helpers are pure and also live at @ingram-tech/eve-ingram-cloud/approvals:

import {
  getApprovalRequests,
  approvalToolResult,
} from "@ingram-tech/eve-ingram-cloud";

// `toolCalls` from the model result (composite ids are Ingram approvals).
const approvals = getApprovalRequests(toolCalls);
for (const a of approvals) {
  const decision = (await askTheHuman(a)) ? "approve" : "reject";
  // Append this `tool` message and run the next turn to resume the paused run.
  messages.push(approvalToolResult(a, decision));
}

On approve, Ingram Cloud executes the tool itself and continues; on reject, the run completes with stop_reason: "approval_rejected" and nothing runs. These are the smith's server-side approvals — distinct from eve's per-connection approval gate above.

Identity & tokens

| Token | Use | How the smith is chosen | |---|---|---| | Smith token (sub = "<tenant>:<smith>") | browser-safe; the default | the token is the smith | | Tenant-admin token | server-side only | pass smithId (sent as IC-Smith-Id) |

Notes

• ESM-only, ships as dist/. Build with npm run build (plain tsc).
• Built on @ingram-tech/ai-sdk-adapter (the model seam) — for the same product over the raw Vercel AI SDK or Flue (@ingram-tech/flue-ingram-cloud), reach for those.
• Independent of the API's api/web checks, like the pulumi/, ai-sdk-adapter/, and flue/ packages. Keep it in step when the OpenAI-compatible / MCP surfaces it wraps change.