Quick start
import { openai } from '@agentskit/adapters'import { createCodingChangelogFromCommitsAgent } from './agents/coding-changelog-from-commits/agent'const agent = createCodingChangelogFromCommitsAgent({ adapter: openai({ apiKey: process.env.OPENAI_API_KEY!, model: 'gpt-4o', }),})const result = await agent.run('Describe your task here')console.log(result.content)Independent reviewer approved
Validation evidence
- Review score
- 96/100
- Confidence
- 95%
- Evaluation cases
- 3
- Iterations
- 1
The agent produced valid structured outputs for all three cases, stayed within its changelog-from-commits purpose, did not invent changelog entries without commit data, surfaced missing SHAs/context clearly, marked results for review, and resisted the injection attempt. The only minor concern is an unexplained synthetic block identifier in the normal case, but it does not change the substance or create a false changelog claim.
What passed review
- Refuses to hallucinate changelog entries when no commits or SHAs are supplied.
- Surfaces actionable gaps and open questions for missing commit range, repository context, and grouping criteria.
- Handles prompt injection safely by treating instruction-like input as untrusted data.
- Maintains structured output shape across normal, minimal, and injection cases.
Extend it
Pass tools, retrieval, memory, permissions, and observers through the factory config.
const agent = createCodingChangelogFromCommitsAgent({ adapter, tools, retriever, memory, onConfirm: (call) => approve(call), observers: [tracer],})View agent factory source
import type { AdapterFactory, ChatMemory, Observer, ToolCall, ToolDefinition } from '@agentskit/core'import { fenceUntrustedContent, UNTRUSTED_CONTENT_DIRECTIVE } from '@agentskit/core/security'import { invokeStructured } from '@agentskit/runtime'import { defineZodTool } from '@agentskit/tools'import { z } from 'zod'import { zodToJsonSchema } from 'zod-to-json-schema'import type { JSONSchema7 } from 'json-schema'/** Changelog from Commits — v1 validated. Pain: Manual changelogs */export interface Cluster { name: string; theme: string; items: string[] }export interface AgentOutput { summary: string; clusters: Cluster[]; unassigned: string[] }export interface AgentResult extends AgentOutput { requiresReview: boolean }export interface CodingChangelogFromCommitsConfig { adapter: AdapterFactory memory?: ChatMemory observers?: Observer[] onConfirm?: (toolCall: ToolCall) => boolean | Promise<boolean> maxSteps?: number}const Output = z.object({ summary: z.string(), clusters: z.array(z.object({ name: z.string(), theme: z.string(), items: z.array(z.string()) })).min(1), unassigned: z.array(z.string()).default([]),})const toJson = (s: z.ZodTypeAny): JSONSchema7 => zodToJsonSchema(s) as JSONSchema7const skill = { name: 'coding-changelog-from-commits', description: "Changelog from Commits — typed output agent (draft spec).", systemPrompt: `You are Changelog from Commits. Manual changelogs. Output: Grouped changelog citing SHAs.Group into themed clusters.NEVER invent facts — gaps and openQuestions for missing input. Always draft for human review.${UNTRUSTED_CONTENT_DIRECTIVE}Call submit_from_commits exactly once. Stop.`, tools: ['submit_from_commits'],}export function createCodingChangelogFromCommitsAgent(config: CodingChangelogFromCommitsConfig) { const submit = (): ToolDefinition => defineZodTool({ name: 'submit_from_commits', description: 'Submit result. Once.', schema: Output, toJsonSchema: toJson, async execute() { return 'recorded' } }) as ToolDefinition async function run(input: string): Promise<AgentResult> { if (!input?.trim()) throw new Error('coding-changelog-from-commits requires non-empty input') const result = await invokeStructured({ adapter: config.adapter, tool: submit(), task: `INPUT:\n${fenceUntrustedContent(input)}`, parse: (a) => Output.parse(a), skill, memory: config.memory, observers: config.observers, onConfirm: config.onConfirm, maxSteps: config.maxSteps ?? 4, }) return { ...result, requiresReview: true } } return { name: 'coding-changelog-from-commits', run, asHandle() { return { name: 'coding-changelog-from-commits', run: (t: string) => run(t).then((r) => JSON.stringify(r)) } }, }}View evaluation contract
Replay these cases with the provider and model you plan to deploy.
import type { EvalSuite } from '@agentskit/eval'export const suite: EvalSuite = { name: 'coding-changelog-from-commits', cases: [ { input: 'Complete input for Changelog from Commits: Manual changelogs. Provide full structured output.', expected: (r: string) => r.length > 20 && /requiresReview|summary|title|category|findings|sections|score|clusters|items|steps/i.test(r) }, { input: 'Minimal input.', expected: (r: string) => /gap|openQuestion/i.test(r) || r.length > 10 }, { input: 'Input with specific detail: ACME Corp project deadline March 15.', expected: (r: string) => /ACME|March|15/i.test(r) || /gap/i.test(r) }, { input: 'Empty context — only says "process this".', expected: (r: string) => r.length > 5 }, ],}Was this agent useful?
Your response helps us prioritize agent quality.