fix(ai): add Moonshot CN Kimi K2.7 metadata

closes #5760

packages/ai/CHANGELOG.md

@@ -2,6 +2,10 @@
 
 ## [Unreleased]
 
+### Fixed
+
+- Fixed Moonshot AI China model metadata to include Kimi K2.7 Code, and omitted unsupported thinking-off payloads for Kimi K2.7 Code models ([#5760](https://github.com/earendil-works/pi/issues/5760)).
+
 ## [0.79.4] - 2026-06-15
 
 ### Fixed

packages/ai/scripts/generate-models.ts

@@ -68,6 +68,8 @@ const KIMI_STATIC_HEADERS = {
 	"User-Agent": "KimiCLI/1.5",
 } as const;
 
+const MOONSHOT_CN_MIRRORED_MODEL_IDS = new Set(["kimi-k2.7-code", "kimi-k2.7-code-highspeed"]);
+
 const TOGETHER_BASE_URL = "https://api.together.ai/v1";
 const TOGETHER_BASE_COMPAT: OpenAICompletionsCompat = {
 	supportsStore: false,
@@ -347,6 +349,15 @@ function applyThinkingLevelMetadata(model: Model<any>): void {
 	if (model.provider === "openai-codex" && supportsOpenAiXhigh(model.id)) {
 		mergeThinkingLevelMap(model, { minimal: "low" });
 	}
+	if (
+		(model.provider === "moonshotai" || model.provider === "moonshotai-cn") &&
+		(model.id === "kimi-k2.7-code" || model.id === "kimi-k2.7-code-highspeed")
+	) {
+		// Kimi K2.7 Code is always-thinking. Official docs say
+		// `thinking: { type: "disabled" }` is rejected, and callers can omit
+		// the thinking parameter to use the enabled default.
+		mergeThinkingLevelMap(model, { off: null });
+	}
 	if (model.provider === "openrouter" && model.id.startsWith("inception/mercury-2")) {
 		// Mercury 2 in instant mode (reasoning_effort: "none") disables tool calling.
 		// Mark "off" unsupported so the openai-completions provider omits the reasoning param
@@ -1262,12 +1273,27 @@ async function loadModelsDevData(): Promise<Model<any>[]> {
 			supportsStrictMode: false,
 			thinkingFormat: "deepseek",
 		};
+		const getMoonshotProviderModels = (key: "moonshotai" | "moonshotai-cn"): Record<string, ModelsDevModel> => {
+			const providerModels = data[key]?.models as Record<string, ModelsDevModel> | undefined;
+			return providerModels ? { ...providerModels } : {};
+		};
+		const moonshotModels = {
+			moonshotai: getMoonshotProviderModels("moonshotai"),
+			"moonshotai-cn": getMoonshotProviderModels("moonshotai-cn"),
+		};
+
+		// models.dev can lag the CN catalog while the global Moonshot catalog already
+		// has the model. Mirror selected current model IDs into moonshotai-cn until
+		// upstream CN metadata catches up.
+		for (const modelId of MOONSHOT_CN_MIRRORED_MODEL_IDS) {
+			const model = moonshotModels.moonshotai[modelId];
+			if (model && !moonshotModels["moonshotai-cn"][modelId]) {
+				moonshotModels["moonshotai-cn"][modelId] = model;
+			}
+		}
 
 		for (const { key, provider, baseUrl } of moonshotVariants) {
-			if (!data[key]?.models) continue;
-
-			for (const [modelId, model] of Object.entries(data[key].models)) {
-				const m = model as ModelsDevModel;
+			for (const [modelId, m] of Object.entries(moonshotModels[key])) {
 				if (m.tool_call !== true) continue;
 
 				models.push({

packages/ai/src/models.generated.ts

@@ -6425,6 +6425,7 @@ export const MODELS = {
 			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: 0.95,
@@ -6563,6 +6564,25 @@ export const MODELS = {
 			contextWindow: 262144,
 			maxTokens: 262144,
 		} satisfies Model<"openai-completions">,
+		"kimi-k2.7-code": {
+			id: "kimi-k2.7-code",
+			name: "Kimi K2.7 Code",
+			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: 0.95,
+				output: 4,
+				cacheRead: 0.19,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 262144,
+		} satisfies Model<"openai-completions">,
 	},
 	"nvidia": {
 		"meta/llama-3.1-70b-instruct": {

packages/ai/src/providers/openai-completions.ts

@@ -564,7 +564,11 @@ function buildParams(
 			preserve_thinking: true,
 		};
 	} else if (compat.thinkingFormat === "deepseek" && model.reasoning) {
-		(params as any).thinking = { type: options?.reasoningEffort ? "enabled" : "disabled" };
+		if (options?.reasoningEffort) {
+			(params as any).thinking = { type: "enabled" };
+		} else if (model.thinkingLevelMap?.off !== null) {
+			(params as any).thinking = { type: "disabled" };
+		}
 		if (options?.reasoningEffort && compat.supportsReasoningEffort) {
 			(params as any).reasoning_effort =
 				model.thinkingLevelMap?.[options.reasoningEffort] ?? options.reasoningEffort;

packages/ai/test/openai-completions-tool-choice.test.ts

@@ -1118,6 +1118,54 @@ describe("openai-completions tool_choice", () => {
 		expect(params.reasoning_effort).toBeUndefined();
 	});
 
+	it("omits disabled thinking for Moonshot Kimi K2.7 Code models", async () => {
+		const cases = [getModel("moonshotai", "kimi-k2.7-code"), getModel("moonshotai-cn", "kimi-k2.7-code")];
+
+		for (const model of cases) {
+			expect(model).toBeDefined();
+			let payload: unknown;
+
+			await streamSimple(
+				model!,
+				{
+					messages: [{ role: "user", content: "Hi", timestamp: Date.now() }],
+				},
+				{
+					apiKey: "test",
+					onPayload: (params: unknown) => {
+						payload = params;
+					},
+				},
+			).result();
+
+			const params = (payload ?? mockState.lastParams) as { thinking?: unknown; reasoning_effort?: string };
+			expect(params.thinking).toBeUndefined();
+			expect(params.reasoning_effort).toBeUndefined();
+		}
+	});
+
+	it("keeps disabled thinking for Moonshot Kimi K2.6 when thinking is off", async () => {
+		const model = getModel("moonshotai-cn", "kimi-k2.6")!;
+		let payload: unknown;
+
+		await streamSimple(
+			model,
+			{
+				messages: [{ role: "user", content: "Hi", timestamp: Date.now() }],
+			},
+			{
+				apiKey: "test",
+				onPayload: (params: unknown) => {
+					payload = params;
+				},
+			},
+		).result();
+
+		const params = (payload ?? mockState.lastParams) as { thinking?: unknown; reasoning_effort?: string };
+		expect(params.thinking).toEqual({ type: "disabled" });
+		expect(params.reasoning_effort).toBeUndefined();
+	});
+
 	it("sends max_tokens for OpenCode completions models", async () => {
 		const cases = [getModel("opencode-go", "kimi-k2.6")!, getModel("opencode", "grok-build-0.1")!] as const;
 

packages/ai/test/supports-xhigh.test.ts

@@ -69,6 +69,15 @@ describe("getSupportedThinkingLevels", () => {
 		expect(getSupportedThinkingLevels(model!)).toEqual(["off", "high"]);
 	});
 
+	it("excludes thinking off for Moonshot Kimi K2.7 Code models", () => {
+		const cases = [getModel("moonshotai", "kimi-k2.7-code"), getModel("moonshotai-cn", "kimi-k2.7-code")];
+
+		for (const model of cases) {
+			expect(model).toBeDefined();
+			expect(getSupportedThinkingLevels(model!)).toEqual(["minimal", "low", "medium", "high"]);
+		}
+	});
+
 	it("includes only high for OpenCode Grok Build", () => {
 		const model = getModel("opencode", "grok-build-0.1");
 		expect(model).toBeDefined();

packages/coding-agent/CHANGELOG.md

@@ -2,6 +2,10 @@
 
 ## [Unreleased]
 
+### Fixed
+
+- Fixed inherited Moonshot AI China model metadata to include Kimi K2.7 Code, and omitted unsupported thinking-off payloads for Kimi K2.7 Code models ([#5760](https://github.com/earendil-works/pi/issues/5760)).
+
 ## [0.79.4] - 2026-06-15
 
 ### New Features