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

fix(ai): support Z.AI GLM-5.2 effort levels

Browse Source 
closes #5770
This commit is contained in:
Armin Ronacher
2026-06-16 14:29:07 +02:00
parent f8a77f47f2
commit 75b0d723c0
5 changed files with 159 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

72
packages/ai/src/models.generated.ts
View File

@@ -3921,7 +3921,7 @@ export const MODELS = {
cost: {
input: 0.15,
output: 0.6,
cacheRead: 0.015,
cacheRead: 0.01,
cacheWrite: 0,
},
contextWindow: 131072,
@@ -6390,6 +6390,25 @@ export const MODELS = {
contextWindow: 262144,
maxTokens: 262144,
} satisfies Model<"openai-completions">,
"kimi-k2.7-code-highspeed": {
id: "kimi-k2.7-code-highspeed",
name: "Kimi K2.7 Code HighSpeed",
api: "openai-completions",
provider: "moonshotai",
baseUrl: "https://api.moonshot.ai/v1",
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"thinkingFormat":"deepseek"},
reasoning: true,
thinkingLevelMap: {"off":null},
input: ["text", "image"],
cost: {
input: 1.9,
output: 8,
cacheRead: 0.38,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 262144,
} satisfies Model<"openai-completions">,
},
"moonshotai-cn": {
"kimi-k2-0711-preview": {
@@ -6537,6 +6556,25 @@ export const MODELS = {
contextWindow: 262144,
maxTokens: 262144,
} satisfies Model<"openai-completions">,
"kimi-k2.7-code-highspeed": {
id: "kimi-k2.7-code-highspeed",
name: "Kimi K2.7 Code HighSpeed",
api: "openai-completions",
provider: "moonshotai-cn",
baseUrl: "https://api.moonshot.cn/v1",
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"thinkingFormat":"deepseek"},
reasoning: true,
thinkingLevelMap: {"off":null},
input: ["text", "image"],
cost: {
input: 1.9,
output: 8,
cacheRead: 0.38,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 262144,
} satisfies Model<"openai-completions">,
},
"nvidia": {
"meta/llama-3.1-70b-instruct": {
@@ -12298,13 +12336,13 @@ export const MODELS = {
reasoning: true,
input: ["text", "image"],
cost: {
input: 0.39,
output: 2.34,
input: 0.385,
output: 2.45,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 65536,
contextWindow: 256000,
maxTokens: 4096,
} satisfies Model<"openai-completions">,
"qwen/qwen3.5-9b": {
id: "qwen/qwen3.5-9b",
@@ -12587,13 +12625,13 @@ export const MODELS = {
reasoning: true,
input: ["text"],
cost: {
input: 0.063,
output: 0.21,
cacheRead: 0.021,
input: 0.066,
output: 0.26,
cacheRead: 0.029,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 4096,
maxTokens: 262144,
} satisfies Model<"openai-completions">,
"thedrummer/rocinante-12b": {
id: "thedrummer/rocinante-12b",
@@ -12774,13 +12812,13 @@ export const MODELS = {
reasoning: true,
input: ["text"],
cost: {
input: 0.125,
input: 0.13,
output: 0.85,
cacheRead: 0.06,
cacheRead: 0.025,
cacheWrite: 0,
},
contextWindow: 131072,
maxTokens: 131070,
maxTokens: 98304,
} satisfies Model<"openai-completions">,
"z-ai/glm-4.5v": {
id: "z-ai/glm-4.5v",
@@ -13214,8 +13252,8 @@ export const MODELS = {
reasoning: false,
input: ["text"],
cost: {
input: 2.5,
output: 7.5,
input: 1.25,
output: 3.75,
cacheRead: 0,
cacheWrite: 0,
},
@@ -16876,8 +16914,9 @@ export const MODELS = {
api: "openai-completions",
provider: "zai",
baseUrl: "https://api.z.ai/api/coding/paas/v4",
compat: {"supportsDeveloperRole":false,"thinkingFormat":"zai","zaiToolStream":true},
compat: {"supportsDeveloperRole":false,"thinkingFormat":"zai","supportsReasoningEffort":true,"zaiToolStream":true},
reasoning: true,
thinkingLevelMap: {"minimal":null,"low":"high","medium":"high","high":"high","xhigh":"max"},
input: ["text"],
cost: {
input: 0,
@@ -16986,8 +17025,9 @@ export const MODELS = {
api: "openai-completions",
provider: "zai-coding-cn",
baseUrl: "https://open.bigmodel.cn/api/coding/paas/v4",
compat: {"supportsDeveloperRole":false,"thinkingFormat":"zai","zaiToolStream":true},
compat: {"supportsDeveloperRole":false,"thinkingFormat":"zai","supportsReasoningEffort":true,"zaiToolStream":true},
reasoning: true,
thinkingLevelMap: {"minimal":null,"low":"high","medium":"high","high":"high","xhigh":"max"},
input: ["text"],
cost: {
input: 0,

12
packages/ai/src/providers/openai-completions.ts
View File

@@ -554,8 +554,18 @@ function buildParams(
}
if (compat.thinkingFormat === "zai" && model.reasoning) {
const zaiParams = params as typeof params & { thinking?: { type: "enabled" | "disabled" } };
const zaiParams = params as Omit<typeof params, "reasoning_effort"> & {
thinking?: { type: "enabled" | "disabled" };
reasoning_effort?: string;
};
zaiParams.thinking = { type: options?.reasoningEffort ? "enabled" : "disabled" };
if (options?.reasoningEffort && compat.supportsReasoningEffort) {
const mappedEffort = model.thinkingLevelMap?.[options.reasoningEffort];
const effort = mappedEffort === undefined ? options.reasoningEffort : mappedEffort;
if (typeof effort === "string") {
zaiParams.reasoning_effort = effort;
}
}
} else if (compat.thinkingFormat === "qwen" && model.reasoning) {
(params as any).enable_thinking = !!options?.reasoningEffort;
} else if (compat.thinkingFormat === "qwen-chat-template" && model.reasoning) {