getcompanion-ai/co-mono
1
0
Fork 0
mirror of https://github.com/getcompanion-ai/co-mono.git synced 2026-04-16 15:02:32 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Add Vertex AI provider with ADC support

Browse source 
- Implement google-vertex provider in packages/ai
- Support ADC (Application Default Credentials) via @google/generative-ai
- Add Gemini model catalog for Vertex AI
- Update packages/coding-agent to handle google-vertex provider
This commit is contained in:
Anton Kuzmenko 2025-12-23 23:03:19 -08:00 • committed by Mario Zechner
parent d747ec6e23
commit 214e7dae15
11 changed files with 788 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

137
packages/ai/scripts/generate-models.ts
View file

@ -644,6 +644,143 @@ async function generateModels() {
];
allModels.push(...antigravityModels);
const VERTEX_BASE_URL = "https://{location}-aiplatform.googleapis.com";
const vertexModels: Model<"google-vertex">[] = [
{
id: "gemini-3-pro-preview",
name: "Gemini 3 Pro Preview (Vertex)",
api: "google-vertex",
provider: "google-vertex",
baseUrl: VERTEX_BASE_URL,
reasoning: true,
input: ["text", "image"],
cost: { input: 2, output: 12, cacheRead: 0.2, cacheWrite: 0 },
contextWindow: 1000000,
maxTokens: 64000,
},
{
id: "gemini-3-flash-preview",
name: "Gemini 3 Flash Preview (Vertex)",
api: "google-vertex",
provider: "google-vertex",
baseUrl: VERTEX_BASE_URL,
reasoning: true,
input: ["text", "image"],
cost: { input: 0.5, output: 3, cacheRead: 0.05, cacheWrite: 0 },
contextWindow: 1048576,
maxTokens: 65536,
},
{
id: "gemini-2.0-flash",
name: "Gemini 2.0 Flash (Vertex)",
api: "google-vertex",
provider: "google-vertex",
baseUrl: VERTEX_BASE_URL,
reasoning: false,
input: ["text", "image"],
cost: { input: 0.1, output: 0.4, cacheRead: 0.025, cacheWrite: 0 },
contextWindow: 1048576,
maxTokens: 8192,
},
{
id: "gemini-2.0-flash-lite",
name: "Gemini 2.0 Flash Lite (Vertex)",
api: "google-vertex",
provider: "google-vertex",
baseUrl: VERTEX_BASE_URL,
reasoning: true,
input: ["text", "image"],
cost: { input: 0.1, output: 0.4, cacheRead: 0.025, cacheWrite: 0 },
contextWindow: 1048576,
maxTokens: 65536,
},
{
id: "gemini-2.5-pro",
name: "Gemini 2.5 Pro (Vertex)",
api: "google-vertex",
provider: "google-vertex",
baseUrl: VERTEX_BASE_URL,
reasoning: true,
input: ["text", "image"],
cost: { input: 1.25, output: 10, cacheRead: 0.31, cacheWrite: 0 },
contextWindow: 1048576,
maxTokens: 65536,
},
{
id: "gemini-2.5-flash",
name: "Gemini 2.5 Flash (Vertex)",
api: "google-vertex",
provider: "google-vertex",
baseUrl: VERTEX_BASE_URL,
reasoning: true,
input: ["text", "image"],
cost: { input: 0.3, output: 2.5, cacheRead: 0.075, cacheWrite: 0 },
contextWindow: 1048576,
maxTokens: 65536,
},
{
id: "gemini-2.5-flash-lite-preview-09-2025",
name: "Gemini 2.5 Flash Lite Preview 09-25 (Vertex)",
api: "google-vertex",
provider: "google-vertex",
baseUrl: VERTEX_BASE_URL,
reasoning: true,
input: ["text", "image"],
cost: { input: 0.1, output: 0.4, cacheRead: 0.025, cacheWrite: 0 },
contextWindow: 1048576,
maxTokens: 65536,
},
{
id: "gemini-2.5-flash-lite",
name: "Gemini 2.5 Flash Lite (Vertex)",
api: "google-vertex",
provider: "google-vertex",
baseUrl: VERTEX_BASE_URL,
reasoning: true,
input: ["text", "image"],
cost: { input: 0.1, output: 0.4, cacheRead: 0.025, cacheWrite: 0 },
contextWindow: 1048576,
maxTokens: 65536,
},
{
id: "gemini-1.5-pro",
name: "Gemini 1.5 Pro (Vertex)",
api: "google-vertex",
provider: "google-vertex",
baseUrl: VERTEX_BASE_URL,
reasoning: false,
input: ["text", "image"],
cost: { input: 1.25, output: 5, cacheRead: 0.3125, cacheWrite: 0 },
contextWindow: 1000000,
maxTokens: 8192,
},
{
id: "gemini-1.5-flash",
name: "Gemini 1.5 Flash (Vertex)",
api: "google-vertex",
provider: "google-vertex",
baseUrl: VERTEX_BASE_URL,
reasoning: false,
input: ["text", "image"],
cost: { input: 0.075, output: 0.3, cacheRead: 0.01875, cacheWrite: 0 },
contextWindow: 1000000,
maxTokens: 8192,
},
{
id: "gemini-1.5-flash-8b",
name: "Gemini 1.5 Flash-8B (Vertex)",
api: "google-vertex",
provider: "google-vertex",
baseUrl: VERTEX_BASE_URL,
reasoning: false,
input: ["text", "image"],
cost: { input: 0.0375, output: 0.15, cacheRead: 0.01, cacheWrite: 0 },
contextWindow: 1000000,
maxTokens: 8192,
},
];
allModels.push(...vertexModels);
// Group by provider and deduplicate by model ID
const providers: Record<string, Record<string, Model<any>>> = {};
for (const model of allModels) {