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.
55 lines
2.6 KiB
TypeScript
55 lines
2.6 KiB
TypeScript
import type { Model, ModelCost } from "../../src/types.ts";
|
|
import { defineProvider, modelsDevModels } from "../define.ts";
|
|
import { KIMI_K3_COST, KIMI_K3_OPENAI_COMPAT, KIMI_OPENAI_COMPAT } from "../families/kimi.ts";
|
|
import { getEffortThinkingLevelMap } from "../reasoning.ts";
|
|
|
|
// Kimi Coding is subscription-backed, so models.dev reports zero cost. Use the
|
|
// equivalent Moonshot API rates to estimate the value of subscription usage.
|
|
const IMPLIED_COSTS: Record<string, ModelCost> = {
|
|
k3: KIMI_K3_COST,
|
|
"k3-256k": KIMI_K3_COST,
|
|
"k3.1-pro": { input: 2, output: 10, cacheRead: 0.2, cacheWrite: 0 },
|
|
"k3.1-pro-highspeed": { input: 4, output: 20, cacheRead: 0.2, cacheWrite: 0 },
|
|
"kimi-for-coding": { input: 0.95, output: 4, cacheRead: 0.19, cacheWrite: 0 },
|
|
"kimi-for-coding-highspeed": { input: 1.9, output: 8, cacheRead: 0.38, cacheWrite: 0 },
|
|
};
|
|
|
|
// Kimi Coding uses Chat Completions, the same protocol as the official Kimi Code client.
|
|
export default defineProvider({
|
|
id: "kimi-coding",
|
|
models: (ctx) =>
|
|
modelsDevModels(ctx, "kimi-code-plan-global", {
|
|
api: "openai-completions",
|
|
baseUrl: "https://api.kimi.com/coding/v1",
|
|
recordReasoning: false,
|
|
map: (model, source): Model<"openai-completions"> => {
|
|
// K3-style models report effort levels and dynamic tool loading (tools declared in
|
|
// later system messages) in https://api.kimi.com/coding/v1/models; models.dev mirrors
|
|
// the effort levels. kimi-for-coding-highspeed reports neither and rejects
|
|
// tool-bearing system messages with a 400.
|
|
const isK3Style = source.reasoningOptions?.some((option) => option.type === "effort") === true;
|
|
const impliedCost = IMPLIED_COSTS[model.id];
|
|
// K3-style models send reasoning_effort, so expose the effort values models.dev lists.
|
|
const effortLevels =
|
|
isK3Style && source.reasoningOptions ? getEffortThinkingLevelMap(source.reasoningOptions) : undefined;
|
|
return {
|
|
...model,
|
|
compat: {
|
|
...(isK3Style ? KIMI_K3_OPENAI_COMPAT : KIMI_OPENAI_COMPAT),
|
|
// All models accept system text after the conversation starts.
|
|
supportsMidConvoSystemMessages: true,
|
|
...(isK3Style ? { supportsMidConvoToolAdditions: true } : {}),
|
|
},
|
|
cost: {
|
|
input: source.cost.input || impliedCost?.input || 0,
|
|
output: source.cost.output || impliedCost?.output || 0,
|
|
cacheRead: source.cost.cacheRead || impliedCost?.cacheRead || 0,
|
|
cacheWrite: source.cost.cacheWrite || impliedCost?.cacheWrite || 0,
|
|
},
|
|
// Kimi Code reports every model as always-thinking.
|
|
thinkingLevelMap: { ...effortLevels, off: null },
|
|
};
|
|
},
|
|
}),
|
|
compat: { "openai-completions": { supportsStrictMode: true } },
|
|
});
|