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.
66 lines
2.8 KiB
TypeScript
66 lines
2.8 KiB
TypeScript
import type { Model } from "../../src/types.ts";
|
|
import { defineProvider, mergeCompat, mergeThinking, modelsDevModels, withInputLimits } from "../define.ts";
|
|
import {
|
|
claude55ThinkingLevels,
|
|
enableClaudeMidConvoEffort,
|
|
supportsClaudeMidConvoEffort,
|
|
supportsClaudeMidConvoSystemMessages,
|
|
} from "../families/anthropic.ts";
|
|
|
|
// Models the API may fall back to, with the price the caller is billed.
|
|
const ALLOWED_FALLBACK_MODELS: Record<string, string[]> = {
|
|
"claude-fable-5": ["claude-opus-4-8", "claude-opus-5"],
|
|
"claude-opus-5": ["claude-opus-4-8"],
|
|
};
|
|
|
|
const MODELS_WITH_1M_CONTEXT = new Set(["claude-opus-4-6", "claude-sonnet-4-6"]);
|
|
const MODELS_55 = new Set(["claude-opus-5-5", "claude-sonnet-5-5", "claude-haiku-5-5"]);
|
|
|
|
export default defineProvider({
|
|
id: "anthropic",
|
|
models: (ctx) =>
|
|
modelsDevModels(ctx, "anthropic", {
|
|
api: "anthropic-messages",
|
|
baseUrl: "https://api.anthropic.com",
|
|
map: (model) => {
|
|
if (MODELS_55.has(model.id)) mergeThinking(model, claude55ThinkingLevels(model.id));
|
|
if (MODELS_WITH_1M_CONTEXT.has(model.id)) model.contextWindow = 1000000;
|
|
return model;
|
|
},
|
|
}),
|
|
finalize: (model) => {
|
|
if (model.api !== "anthropic-messages") return;
|
|
const messagesModel = model as Model<"anthropic-messages">;
|
|
if (supportsClaudeMidConvoEffort(model.id)) enableClaudeMidConvoEffort(messagesModel);
|
|
if (supportsClaudeMidConvoSystemMessages(model.id)) {
|
|
mergeCompat(messagesModel, { supportsMidConvoSystemMessages: true, supportsMidConvoToolChanges: true });
|
|
}
|
|
mergeCompat(messagesModel, { supportsStrictTools: true });
|
|
// Ephemeral entries have a hard five-minute lifetime; `ttl: "1h"` extends
|
|
// it to one hour. Only direct Anthropic is annotated so cache warming does
|
|
// not assume equivalent behavior through proxies.
|
|
// https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching
|
|
model.promptCache = { short: 300, long: 3600 };
|
|
withInputLimits(model, {
|
|
maxRequestBytes: 32 * 1024 * 1024,
|
|
images: { maxPerRequest: model.contextWindow === 200000 ? 100 : 600 },
|
|
});
|
|
},
|
|
finalizeAll: (models) => {
|
|
const modelsById = new Map(models.map((model) => [model.id, model as Model<"anthropic-messages">]));
|
|
for (const [modelId, fallbackModelIds] of Object.entries(ALLOWED_FALLBACK_MODELS)) {
|
|
const model = modelsById.get(modelId);
|
|
if (!model) continue;
|
|
const compatibleFallbackModelIds = model.compat?.supportsMidConvoEffort
|
|
? fallbackModelIds.filter(supportsClaudeMidConvoEffort)
|
|
: fallbackModelIds;
|
|
const allowedFallbackModels = compatibleFallbackModelIds.flatMap((fallbackModelId) => {
|
|
const fallbackModel = modelsById.get(fallbackModelId);
|
|
return fallbackModel
|
|
? [{ provider: fallbackModel.provider, model: fallbackModel.id, cost: fallbackModel.cost }]
|
|
: [];
|
|
});
|
|
if (allowedFallbackModels.length > 0) mergeCompat(model, { allowedFallbackModels });
|
|
}
|
|
},
|
|
});
|