Tools provided
Tools the agent exposes — your AI client calls them automatically when it needs them.
- run_full — Orchestrated path: diff the supplied baseline against the current contract, flag the breaking changes, compute the semver impact and next version, generate the OpenAPI document, TypeScript and PHP SDKs and the changelog.
- analyze — Run pure deterministic drift analysis over provided baseline and current contracts with no model call and return scored breaking and non-breaking findings.
- generate_openapi — Build a fresh OpenAPI 3.0 document for the current endpoints — the generation step on its own.
- generate_sdks — Generate deterministic TypeScript and PHP client SDK stubs for the current endpoints, one method per endpoint.
- classify_semver — Diff the contracts and return just the semver impact — major, minor or patch — the version-bump decision on its own.
- build_changelog — Diff the contracts and return the human-readable changelog lines, worst first, with breaking entries tagged.
- list_capabilities — List the agent's static capabilities: the available tools and the drift classification rules that decide what counts as breaking versus non-breaking. Useful for discovery.
- plan_inputs — Plan the inputs for a tool: returns the clarifying questions, the JSON schema and a ready-to-edit example.
- discover_intent — Understand your goal and co-design the exact input through clarifying questions before running.
- open_form — Opens the guided form to collect the service and the two contracts to compare. The entry point for running the agent on your own data.
- run_form — Internal: invoked by the guided form when the user submits. Not for direct use.
