models: EndpointAdmin and PublisherAdmin wrap every remaining method of the
owned resources (84 call table rows, 132 Discovery methods covered, v1beta1
twins, IAM, operations, responses, export, config, enableModel); planner
rejects undeclared body keys; VertexModel::TurnBuilder replays model turns
with every thoughtSignature; Lyria WAV mime from bytes; veo-3.1 default.
runtime: v1beta1 feedbackEntries, A2A gateway (40 rpcs), a2aTasks, task store
records, scoped operations, beta twin flag (103 rows, 214 methods covered);
checker verifies twins, a2aEndpoint patterns and coverage.
example: admin routes for both parts. SPECs: live results moved from
Unverified to Verified live (Veo, Lyria, thought signatures, v1beta1 routes).
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
One call table verified against Discovery (29 calls), live-verified read-only
with an express key and a service account token, /agent/models example routes.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
GoogleClient gets every verb and stream_json (SSE and plain JSON), typed
Content/Part/Tool/GenerateRequest with the LanguageModel seam, CloudContext
resource names, long-running operation polling and pagination, OAuth bearer
tokens via GOOGLE_ACCESS_TOKEN. Example scaffold: one stub per agent module
under example/app/agent, wildcard builds, locust excludes /voice /google
/agent. plans/16-agent-platform.md splits the work into nine modules.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>