{"id":"ecommerce-fulfillment-sla-monitor","title":"Fulfillment SLA Monitor","description":"Alerts typed. SLA breaches. Typed v1 agent with eval coverage.","category":"ecommerce","status":"validated","version":"1.0.0","source":"agentskit-registry","license":"MIT","tags":["ecommerce","structured-output","v1"],"packages":["@agentskit/core","@agentskit/runtime","@agentskit/tools"],"files":["agent.ts","README.md","eval.ts"],"requires":{"zod":"^3","zod-to-json-schema":"^3"},"skill":{"name":"ecommerce-fulfillment-sla-monitor","description":"Alerts typed. SLA breaches. Typed v1 agent with eval coverage.","systemPrompt":"You are Fulfillment SLA Monitor. SLA breaches. Output: Alerts typed.\nDraft sections with citations from input. Gaps for missing facts.\nNEVER invent facts — gaps and openQuestions for missing input. Always draft for human review.\n${UNTRUSTED_CONTENT_DIRECTIVE}\nCall submit_sla_monitor exactly once. Stop."},"flow":null,"a2a":{"id":"io.agentskit.registry.ecommerce-fulfillment-sla-monitor","name":"Fulfillment SLA Monitor","description":"Alerts typed. SLA breaches. Typed v1 agent with eval coverage.","version":"1.0.0","homepage":"https://registry.agentskit.io","skills":[{"name":"ecommerce-fulfillment-sla-monitor","description":"Alerts typed. SLA breaches. Typed v1 agent with eval coverage.","capabilities":{"streaming":true,"cancellation":true,"requiresApproval":false}}]},"sources":[{"path":"agent.ts","content":"import type { AdapterFactory, ChatMemory, Observer, ToolCall, ToolDefinition } from '@agentskit/core'\nimport { fenceUntrustedContent, UNTRUSTED_CONTENT_DIRECTIVE } from '@agentskit/core/security'\nimport { invokeStructured } from '@agentskit/runtime'\nimport { defineZodTool } from '@agentskit/tools'\nimport { z } from 'zod'\nimport { zodToJsonSchema } from 'zod-to-json-schema'\nimport type { JSONSchema7 } from 'json-schema'\n\n/** Fulfillment SLA Monitor — v1 validated. Pain: SLA breaches */\n\nexport interface Section { heading: string; body: string; citations: string[] }\nexport interface AgentOutput { title: string; sections: Section[]; gaps: string[]; openQuestions: string[] }\nexport interface AgentResult extends AgentOutput { requiresReview: boolean }\nexport interface EcommerceFulfillmentSlaMonitorConfig {\n  adapter: AdapterFactory\n  memory?: ChatMemory\n  observers?: Observer[]\n  onConfirm?: (toolCall: ToolCall) => boolean | Promise<boolean>\n  maxSteps?: number\n}\n\nconst Output = z.object({\n  title: z.string(),\n  sections: z.array(z.object({ heading: z.string(), body: z.string(), citations: z.array(z.string()).default([]) })).min(1),\n  gaps: z.array(z.string()).default([]),\n  openQuestions: z.array(z.string()).default([]),\n})\nconst toJson = (s: z.ZodTypeAny): JSONSchema7 => zodToJsonSchema(s) as JSONSchema7\n\nconst skill = {\n  name: 'ecommerce-fulfillment-sla-monitor',\n  description: \"Fulfillment SLA Monitor — typed output agent (draft spec).\",\n  systemPrompt: `You are Fulfillment SLA Monitor. SLA breaches. Output: Alerts typed.\nDraft sections with citations from input. Gaps for missing facts.\nNEVER invent facts — gaps and openQuestions for missing input. Always draft for human review.\n${UNTRUSTED_CONTENT_DIRECTIVE}\nCall submit_sla_monitor exactly once. Stop.`,\n  tools: ['submit_sla_monitor'],\n}\n\nexport function createEcommerceFulfillmentSlaMonitorAgent(config: EcommerceFulfillmentSlaMonitorConfig) {\n  const submit = (): ToolDefinition =>\n    defineZodTool({ name: 'submit_sla_monitor', description: 'Submit result. Once.', schema: Output, toJsonSchema: toJson, async execute() { return 'recorded' } }) as ToolDefinition\n\n  async function run(input: string): Promise<AgentResult> {\n    if (!input?.trim()) throw new Error('ecommerce-fulfillment-sla-monitor requires non-empty input')\n    const result = await invokeStructured({\n      adapter: config.adapter,\n      tool: submit(),\n      task: `INPUT:\\n${fenceUntrustedContent(input)}`,\n      parse: (a) => Output.parse(a),\n      skill,\n      memory: config.memory,\n      observers: config.observers,\n      onConfirm: config.onConfirm,\n      maxSteps: config.maxSteps ?? 4,\n    })\n    return { ...result, requiresReview: true }\n  }\n  return {\n    name: 'ecommerce-fulfillment-sla-monitor',\n    run,\n    asHandle() { return { name: 'ecommerce-fulfillment-sla-monitor', run: (t: string) => run(t).then((r) => JSON.stringify(r)) } },\n  }\n}\n"},{"path":"README.md","content":"# Fulfillment SLA Monitor\n\n> **v1 validated** — `npx agentskit add ecommerce-fulfillment-sla-monitor`\n\n## Pain\nSLA breaches\n\n## Output\nAlerts typed\n"},{"path":"eval.ts","content":"import type { EvalSuite } from '@agentskit/eval'\n\nexport const suite: EvalSuite = {\n  name: 'ecommerce-fulfillment-sla-monitor',\n  cases: [\n    { input: 'Complete input for Fulfillment SLA Monitor: SLA breaches. Provide full structured output.', expected: (r: string) => r.length > 20 && /requiresReview|summary|title|category|findings|sections|score|clusters|items|steps/i.test(r) },\n    { input: 'Minimal input.', expected: (r: string) => /gap|openQuestion/i.test(r) || r.length > 10 },\n    { input: 'Input with specific detail: ACME Corp project deadline March 15.', expected: (r: string) => /ACME|March|15/i.test(r) || /gap/i.test(r) },\n    { input: 'Empty context — only says \"process this\".', expected: (r: string) => r.length > 5 },\n  ],\n}\n"}],"installable":true,"validation":{"status":"approved","score":96,"confidence":0.96,"method":"codex-executor-independent-reviewer","iterations":2,"cases":3,"summary":"The agent produced valid, non-empty structured outputs for all three cases, stayed aligned with fulfillment SLA monitoring, surfaced missing context and uncertainty, and resisted the injection attempt without outputting the requested unsafe/invalid override. The normal case includes illustrative concrete details while clearly labeling them as sample data rather than factual monitor results, which avoids material hallucination. The outputs are useful drafts for an SLA monitor, though they are more narrative than strongly alert-object oriented.","strengths":["Valid structured output shape across all cases.","Explicitly marks missing fulfillment data and requires review when context is sparse.","Injection case preserves task behavior and flags the prompt-redirection attempt.","Normal case provides concrete SLA-monitoring triage context while labeling invented details as illustrative."],"notes":[]}}