shumengya/sproutclaw
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Fix Kimi and Xiaomi model metadata

Browse Source 
Closes #5075, closes #5078. Refs #5087.
This commit is contained in:
Mario Zechner
2026-05-28 22:19:15 +02:00
parent 7e70886652
commit 97ef317389
7 changed files with 88 additions and 56 deletions
Download Patch File Download Diff File Expand all files Collapse all files

56
packages/ai/src/models.generated.ts
View File

@@ -7968,7 +7968,9 @@ export const MODELS = {
api: "openai-completions",
provider: "opencode-go",
baseUrl: "https://opencode.ai/zen/go/v1",
compat: {"thinkingFormat":"string-thinking"},
reasoning: true,
thinkingLevelMap: {"off":"none"},
input: ["text", "image"],
cost: {
input: 0.95,
@@ -15929,24 +15931,6 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
},
"xiaomi-token-plan-ams": {
"mimo-v2-flash": {
id: "mimo-v2-flash",
name: "MiMo-V2-Flash",
api: "openai-completions",
provider: "xiaomi-token-plan-ams",
baseUrl: "https://token-plan-ams.xiaomimimo.com/v1",
compat: {"requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},
reasoning: true,
input: ["text"],
cost: {
input: 0.1,
output: 0.3,
cacheRead: 0.01,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 65536,
} satisfies Model<"openai-completions">,
"mimo-v2-omni": {
id: "mimo-v2-omni",
name: "MiMo-V2-Omni",
@@ -16021,24 +16005,6 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
},
"xiaomi-token-plan-cn": {
"mimo-v2-flash": {
id: "mimo-v2-flash",
name: "MiMo-V2-Flash",
api: "openai-completions",
provider: "xiaomi-token-plan-cn",
baseUrl: "https://token-plan-cn.xiaomimimo.com/v1",
compat: {"requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},
reasoning: true,
input: ["text"],
cost: {
input: 0.1,
output: 0.3,
cacheRead: 0.01,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 65536,
} satisfies Model<"openai-completions">,
"mimo-v2-omni": {
id: "mimo-v2-omni",
name: "MiMo-V2-Omni",
@@ -16113,24 +16079,6 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
},
"xiaomi-token-plan-sgp": {
"mimo-v2-flash": {
id: "mimo-v2-flash",
name: "MiMo-V2-Flash",
api: "openai-completions",
provider: "xiaomi-token-plan-sgp",
baseUrl: "https://token-plan-sgp.xiaomimimo.com/v1",
compat: {"requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},
reasoning: true,
input: ["text"],
cost: {
input: 0.1,
output: 0.3,
cacheRead: 0.01,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 65536,
} satisfies Model<"openai-completions">,
"mimo-v2-omni": {
id: "mimo-v2-omni",
name: "MiMo-V2-Omni",

7
packages/ai/src/providers/openai-completions.ts
View File

@@ -594,6 +594,13 @@ function buildParams(
if (options?.reasoningEffort && compat.supportsReasoningEffort) {
togetherParams.reasoning_effort = model.thinkingLevelMap?.[options.reasoningEffort] ?? options.reasoningEffort;
}
} else if (compat.thinkingFormat === "string-thinking" && model.reasoning) {
const stringThinkingParams = params as typeof params & { thinking?: string };
if (options?.reasoningEffort) {
stringThinkingParams.thinking = model.thinkingLevelMap?.[options.reasoningEffort] ?? options.reasoningEffort;
} else if (model.thinkingLevelMap?.off !== null) {
stringThinkingParams.thinking = model.thinkingLevelMap?.off ?? "none";
}
} else if (options?.reasoningEffort && model.reasoning && compat.supportsReasoningEffort) {
// OpenAI-style reasoning_effort
(params as any).reasoning_effort = model.thinkingLevelMap?.[options.reasoningEffort] ?? options.reasoningEffort;

12
packages/ai/src/types.ts
View File

@@ -387,8 +387,16 @@ export interface OpenAICompletionsCompat {
requiresThinkingAsText?: boolean;
/** Whether all replayed assistant messages must include an empty reasoning_content field when reasoning is enabled. Default: auto-detected from URL. */
requiresReasoningContentOnAssistantMessages?: boolean;
/** Format for reasoning/thinking parameter. "openai" uses reasoning_effort, "openrouter" uses reasoning: { effort }, "deepseek" uses thinking: { type } plus reasoning_effort, "together" uses reasoning: { enabled } plus reasoning_effort when supported, "zai" uses top-level enable_thinking: boolean, "qwen" uses top-level enable_thinking: boolean, and "qwen-chat-template" uses chat_template_kwargs.enable_thinking. Default: "openai". */
thinkingFormat?: "openai" | "openrouter" | "deepseek" | "together" | "zai" | "qwen" | "qwen-chat-template";
/** Format for reasoning/thinking parameter. "openai" uses reasoning_effort, "openrouter" uses reasoning: { effort }, "deepseek" uses thinking: { type } plus reasoning_effort, "together" uses reasoning: { enabled } plus reasoning_effort when supported, "zai" uses top-level enable_thinking: boolean, "qwen" uses top-level enable_thinking: boolean, "qwen-chat-template" uses chat_template_kwargs.enable_thinking, and "string-thinking" uses top-level thinking: string. Default: "openai". */
thinkingFormat?:
| "openai"
| "openrouter"
| "deepseek"
| "together"
| "zai"
| "qwen"
| "qwen-chat-template"
| "string-thinking";
/** OpenRouter-specific routing preferences. Only used when baseUrl points to OpenRouter. */
openRouterRouting?: OpenRouterRouting;
/** Vercel AI Gateway routing preferences. Only used when baseUrl points to Vercel AI Gateway. */