Changelog Generator

Write a user-facing changelog from git commits, grouped by type, in Keep a Changelog, semantic or bullet format.

Pay by wallet (x402) AI-generated changelog-generate

Example

Example answer

{
  "format": "",
  "sections": [],
  "commit_count": 0,
  "breaking_changes": [],
  "changelog_markdown": "## [Unreleased]\n\nNo changes yet.",
  "version_suggestion": "patch"
}

Inputs

Field	Type	Required	What it is
`format`	string	No	—
`commits`	array	No	Array of {message, author, date}
`raw_log`	string	No	—

Output fields

How reliably each field appears in a successful answer.

Field	Type	Appears
`sections`	array	Always (present in every successful answer)
`breaking_changes`	array	Always (present in every successful answer)
`changelog_markdown`	string	Always (present in every successful answer)
`version_suggestion`	string	Always (present in every successful answer)

How to call it

The same tool through each route. MCP clients reach it through Strale’s server at https://api.strale.io/mcp; the call below is what the agent sends.

# Needs an API key. max_price_cents caps what this call may cost.
curl -X POST https://api.strale.io/v1/do \
  -H "Authorization: Bearer $STRALE_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
    "capability_slug": "changelog-generate",
    "inputs": {
      "commits": [
        {
          "message": "Add user authentication"
        },
        {
          "message": "Fix login validation bug"
        },
        {
          "message": "Update dependencies"
        }
      ]
    },
    "max_price_cents": 3
  }'

{
  "tool": "strale_execute",
  "arguments": {
    "slug": "changelog-generate",
    "inputs": {
      "commits": [
        {
          "message": "Add user authentication"
        },
        {
          "message": "Fix login validation bug"
        },
        {
          "message": "Update dependencies"
        }
      ]
    },
    "max_price_cents": 3
  }
}

import { Strale } from "straleio";

const strale = new Strale({ apiKey: process.env.STRALE_API_KEY! });
const result = await strale.do({
  capability_slug: "changelog-generate",
  inputs: {
    "commits": [
      {
        "message": "Add user authentication"
      },
      {
        "message": "Fix login validation bug"
      },
      {
        "message": "Update dependencies"
      }
    ]
  },
  max_price_cents: 3,
});

import os
from straleio import Strale, DoRequest

strale = Strale(api_key=os.environ["STRALE_API_KEY"])
result = strale.do(DoRequest(
    capability_slug="changelog-generate",
    inputs={
        "commits": [
            {
                "message": "Add user authentication",
            },
            {
                "message": "Fix login validation bug",
            },
            {
                "message": "Update dependencies",
            },
        ],
    },
    max_price_cents=3,
))

# No account. The first request answers 402 with the price in USDC;
# an x402 client pays it from your wallet and repeats the request.
curl -i -X POST https://api.strale.io/x402/v2/changelog-generate \
  -H 'Content-Type: application/json' \
  -d '{
    "commits": [
      {
        "message": "Add user authentication"
      },
      {
        "message": "Fix login validation bug"
      },
      {
        "message": "Update dependencies"
      }
    ]
  }'

Limitations

User-facing changes can be misidentified
AI-generated changelog from commit messages or diffs — may not correctly identify user-facing impact vs internal changes
What to do instead: Use conventional commit prefixes (feat:, fix:, chore:) in your commits for more accurate categorisation