Table driven REST (509 rows verified against vendor specs by tools/check_spec.py),
WebSockets over the src/google/live client, neutral SpeechSynthesizer /
SpeechRecognizer seam, /ai/audio demo with dry runs, 110 package tests and 5
route tests. PlayHT has no public API; LeMUR is gone from AssemblyAI's spec.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Adds molo::google::apis (api_catalog) as the code source of truth,
src/google/APIS.md, a Required APIs section per module SPEC, and the
vendor key consoles in src/llm/SPEC.md. Placeholder project example-214512124.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
121-call table checked against the OpenAI OpenAPI document, admin-key-only
client, destructive guards, WebhookVerifier (Standard Webhooks HMAC-SHA256),
demo routes under /ai/openai/admin, local and opt-in live tests.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
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>
Data plane per the computer use quickstart and SDK 2.6.0 source: signJwt
minted JWT, /cdp /tabs /cdp_ws_endpoint over HTTP with routing headers, CDP
over the live WsClient with capped reconnect. Operations methods wrapped,
input/output chunk shapes settled from the SDK, ComputerUse moved off execute.
Execution paths remain verified by Discovery, docs and SDK only.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
86-row call table checked against Google discovery documents, typed
services, local approval ledger, live read-only tests, /agent/registry demo.
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>
Typed results with hard caps, one call table checked against Discovery
(tools/check_discovery.py), live read-only probe, /agent/sandbox demo.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
DirectModel over GoogleClient with thought-signature replay, discovery check
script, live verified against the real model (function calling, transfer, MCP).
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>