mirror of
https://github.com/badlogic/pi-mono.git
synced 2026-11-05 23:37:25 +00:00
2e0f175bd5
This builds the model catalog from per-provider definitions and models.dev v2 data. It eplacer `generate-models.ts` with one `defineProvider()` file per built-in provider, shared model-family rules (Claude, GPT, DeepSeek, Kimi, Google), and source adapters. models.dev is read through its v2 API. Outputs and CLI flags are unchanged.
43 lines
1.8 KiB
TypeScript
43 lines
1.8 KiB
TypeScript
import { defineProvider, modelsDevModels } from "../define.ts";
|
|
import { googleThinkingLevels } from "../families/google.ts";
|
|
import { modelsDevChatModels } from "../sources/models-dev.ts";
|
|
import { GOOGLE_ALIAS_TARGETS } from "./google.ts";
|
|
|
|
export default defineProvider({
|
|
id: "google-vertex",
|
|
models: (ctx) => {
|
|
const sources = new Map(
|
|
modelsDevChatModels(ctx.sources.modelsDev, "google-vertex").map((model) => [model.id, model]),
|
|
);
|
|
return modelsDevModels(ctx, "google-vertex", {
|
|
api: "google-vertex",
|
|
baseUrl: "https://{location}-aiplatform.googleapis.com",
|
|
recordReasoning: false,
|
|
// The models.dev catalog also includes Claude, OpenAI, and other MaaS models
|
|
// that do not use the @google/genai Gemini streaming path.
|
|
include: (source) => source.id.startsWith("gemini-") && source.id !== "gemini-3.1-flash-lite-preview",
|
|
map: (model, aliasSource) => {
|
|
const target = GOOGLE_ALIAS_TARGETS[model.id];
|
|
const source = (target && sources.get(target)) || aliasSource;
|
|
const thinkingLevelMap = googleThinkingLevels(model.id, source.reasoningOptions);
|
|
return {
|
|
...model,
|
|
reasoning: source.reasoning,
|
|
...(thinkingLevelMap ? { thinkingLevelMap } : {}),
|
|
input: source.imageInput ? ["text", "image"] : ["text"],
|
|
cost: {
|
|
input: source.cost.input || 0,
|
|
output: source.cost.output || 0,
|
|
// models.dev reports Vertex cache_read/cache_write values for Gemini 2.5 Flash that
|
|
// do not match the official Gemini API standard pricing table. pi only accounts
|
|
// cachedContentTokenCount as cacheRead.
|
|
cacheRead: model.id === "gemini-2.5-flash" ? 0.03 : source.cost.cacheRead || 0,
|
|
cacheWrite: 0,
|
|
},
|
|
contextWindow: source.contextWindow || 4096,
|
|
maxTokens: source.maxTokens || 4096,
|
|
};
|
|
},
|
|
});
|
|
},
|
|
});
|