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.
67 lines
2.4 KiB
TypeScript
67 lines
2.4 KiB
TypeScript
// DeepSeek V4 models on OpenAI-compatible hosts.
|
|
|
|
import type { Model, OpenAICompletionsCompat } from "../../src/types.ts";
|
|
import { type ChatModel, mergeCompat, mergeThinking } from "../define.ts";
|
|
|
|
export const DEEPSEEK_COMPAT: OpenAICompletionsCompat = {
|
|
requiresReasoningContentOnAssistantMessages: true,
|
|
thinkingFormat: "deepseek",
|
|
};
|
|
|
|
export const DEEPSEEK_V4_THINKING_LEVEL_MAP = {
|
|
minimal: null,
|
|
low: null,
|
|
medium: null,
|
|
high: "high",
|
|
max: "max",
|
|
} as const;
|
|
export const DEEPSEEK_V4_FLASH_THINKING_LEVEL_MAP = {
|
|
...DEEPSEEK_V4_THINKING_LEVEL_MAP,
|
|
low: "low",
|
|
} as const;
|
|
// Azure Foundry rejects DeepSeek's own max effort.
|
|
const AZURE_DEEPSEEK_V4_THINKING_LEVEL_MAP = {
|
|
minimal: null,
|
|
low: "low",
|
|
medium: "medium",
|
|
high: "high",
|
|
xhigh: null,
|
|
max: null,
|
|
} as const;
|
|
|
|
// Qwen Token Plan serves DeepSeek V4 through Qwen's own thinking format.
|
|
const QWEN_FORMAT_PROVIDERS = new Set(["qwen-token-plan", "qwen-token-plan-cn", "qwen-token-plan-individual"]);
|
|
// These hosts accept native reasoning efforts instead of DeepSeek's thinking toggle.
|
|
const NATIVE_EFFORT_PROVIDERS = new Set(["openrouter", "opencode"]);
|
|
|
|
function isDeepSeekV4(model: ChatModel): model is Model<"openai-completions"> {
|
|
return model.api === "openai-completions" && model.id.includes("deepseek-v4");
|
|
}
|
|
|
|
/** DeepSeek V4 needs its reasoning content replayed on every host. */
|
|
export function applyDeepSeekCompatRules(model: ChatModel): void {
|
|
if (!isDeepSeekV4(model) || QWEN_FORMAT_PROVIDERS.has(model.provider)) return;
|
|
mergeCompat(
|
|
model,
|
|
NATIVE_EFFORT_PROVIDERS.has(model.provider)
|
|
? { requiresReasoningContentOnAssistantMessages: DEEPSEEK_COMPAT.requiresReasoningContentOnAssistantMessages }
|
|
: DEEPSEEK_COMPAT,
|
|
);
|
|
}
|
|
|
|
/** DeepSeek V4 effort levels when the host did not report its own. */
|
|
export function applyDeepSeekFamilyRules(model: ChatModel): void {
|
|
if (!isDeepSeekV4(model) || model.thinkingLevelMap !== undefined) return;
|
|
if (model.provider === "openrouter") {
|
|
mergeThinking(model, { ...DEEPSEEK_V4_THINKING_LEVEL_MAP, xhigh: "xhigh", max: null });
|
|
} else if (model.provider === "azure") {
|
|
mergeThinking(model, AZURE_DEEPSEEK_V4_THINKING_LEVEL_MAP);
|
|
} else if (
|
|
(model.provider === "deepseek" || model.provider === "opencode" || model.provider === "opencode-go") &&
|
|
model.id.includes("deepseek-v4-flash")
|
|
) {
|
|
mergeThinking(model, DEEPSEEK_V4_FLASH_THINKING_LEVEL_MAP);
|
|
} else {
|
|
mergeThinking(model, DEEPSEEK_V4_THINKING_LEVEL_MAP);
|
|
}
|
|
}
|