feat(ai): add Xiaomi MiMo provider (#4005)

* fix(ai): include minimax-cn in cross-provider-handoff matrix

* feat(ai): add Xiaomi MiMo provider

Adds Xiaomi MiMo as an openai-completions-compatible provider.

- packages/ai: register provider in types/KnownProvider, env-api-keys (XIAOMI_API_KEY), generate-models, models.generated.ts, overflow util, README, CHANGELOG
- packages/ai/test: extend stream, tokens, abort, empty, context-overflow, overflow, image-tool-result, tool-call-without-result, total-tokens, unicode-surrogate, cross-provider-handoff matrices with Xiaomi
- packages/coding-agent: default model (mimo-v2.5-pro), display name (Xiaomi MiMo), CLI env var docs, README, docs/providers.md

closes #3912

---------

Co-authored-by: Mario Zechner <badlogicgames@gmail.com>

packages/ai/CHANGELOG.md

@@ -2,11 +2,17 @@
 
 ## [Unreleased]
 
+<<<<<<< feat/add-xiaomi-provider
+### Added
+
+- Added Xiaomi MiMo provider (openai-completions compatible) with `XIAOMI_API_KEY` authentication.
+=======
 ## [0.71.1] - 2026-05-01
 
 ### Added
 
 - Added `websocket-cached` transport support for OpenAI Codex Responses used with ChatGPT subscription auth. This keeps the same WebSocket open for a session and, after the first request, sends only new conversation items instead of resending the full chat history when possible.
+>>>>>>> main
 
 ## [0.71.0] - 2026-04-30
 

packages/ai/README.md

@@ -69,6 +69,7 @@ Unified LLM API with automatic model discovery, provider configuration, token an
 - **OpenCode Go**
 - **Fireworks** (uses Anthropic-compatible API)
 - **Kimi For Coding** (Moonshot AI, uses Anthropic-compatible API)
+- **Xiaomi MiMo** (uses OpenAI-compatible API)
 - **Any OpenAI-compatible API**: Ollama, vLLM, LM Studio, etc.
 
 ## Installation

packages/ai/scripts/generate-models.ts

@@ -834,6 +834,32 @@ async function loadModelsDevData(): Promise<Model<any>[]> {
 			}
 		}
 
+		// Process Xiaomi MiMo models
+		if (data.xiaomi?.models) {
+			for (const [modelId, model] of Object.entries(data.xiaomi.models)) {
+				const m = model as ModelsDevModel;
+				if (m.tool_call !== true) continue;
+
+				models.push({
+					id: modelId,
+					name: m.name || modelId,
+					api: "openai-completions",
+					provider: "xiaomi",
+					baseUrl: "https://api.xiaomimimo.com/v1",
+					reasoning: m.reasoning === true,
+					input: m.modalities?.input?.includes("image") ? ["text", "image"] : ["text"],
+					cost: {
+						input: m.cost?.input || 0,
+						output: m.cost?.output || 0,
+						cacheRead: m.cost?.cache_read || 0,
+						cacheWrite: m.cost?.cache_write || 0,
+					},
+					contextWindow: m.limit?.context || 4096,
+					maxTokens: m.limit?.output || 4096,
+				});
+			}
+		}
+
 		console.log(`Loaded ${models.length} tool-capable models from models.dev`);
 		return models;
 	} catch (error) {

packages/ai/src/env-api-keys.ts

@@ -122,6 +122,7 @@ function getApiKeyEnvVars(provider: string): readonly string[] | undefined {
 		"kimi-coding": "KIMI_API_KEY",
 		"cloudflare-workers-ai": "CLOUDFLARE_API_KEY",
 		"cloudflare-ai-gateway": "CLOUDFLARE_API_KEY",
+		xiaomi: "XIAOMI_API_KEY",
 	};
 
 	const envVar = envMap[provider];

packages/ai/src/models.generated.ts

@@ -16231,6 +16231,93 @@ export const MODELS = {
 			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
 	},
+	"xiaomi": {
+		"mimo-v2-flash": {
+			id: "mimo-v2-flash",
+			name: "MiMo-V2-Flash",
+			api: "openai-completions",
+			provider: "xiaomi",
+			baseUrl: "https://api.xiaomimimo.com/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.1,
+				output: 0.3,
+				cacheRead: 0.01,
+				cacheWrite: 0,
+			},
+			contextWindow: 256000,
+			maxTokens: 64000,
+		} satisfies Model<"openai-completions">,
+		"mimo-v2-omni": {
+			id: "mimo-v2-omni",
+			name: "MiMo-V2-Omni",
+			api: "openai-completions",
+			provider: "xiaomi",
+			baseUrl: "https://api.xiaomimimo.com/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.4,
+				output: 2,
+				cacheRead: 0.08,
+				cacheWrite: 0,
+			},
+			contextWindow: 256000,
+			maxTokens: 128000,
+		} satisfies Model<"openai-completions">,
+		"mimo-v2-pro": {
+			id: "mimo-v2-pro",
+			name: "MiMo-V2-Pro",
+			api: "openai-completions",
+			provider: "xiaomi",
+			baseUrl: "https://api.xiaomimimo.com/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 1,
+				output: 3,
+				cacheRead: 0.2,
+				cacheWrite: 0,
+			},
+			contextWindow: 1000000,
+			maxTokens: 128000,
+		} satisfies Model<"openai-completions">,
+		"mimo-v2.5": {
+			id: "mimo-v2.5",
+			name: "MiMo-V2.5",
+			api: "openai-completions",
+			provider: "xiaomi",
+			baseUrl: "https://api.xiaomimimo.com/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.4,
+				output: 2,
+				cacheRead: 0.08,
+				cacheWrite: 0,
+			},
+			contextWindow: 1048576,
+			maxTokens: 131072,
+		} satisfies Model<"openai-completions">,
+		"mimo-v2.5-pro": {
+			id: "mimo-v2.5-pro",
+			name: "MiMo-V2.5-Pro",
+			api: "openai-completions",
+			provider: "xiaomi",
+			baseUrl: "https://api.xiaomimimo.com/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 1,
+				output: 3,
+				cacheRead: 0.2,
+				cacheWrite: 0,
+			},
+			contextWindow: 1048576,
+			maxTokens: 131072,
+		} satisfies Model<"openai-completions">,
+	},
 	"zai": {
 		"glm-4.5-air": {
 			id: "glm-4.5-air",

packages/ai/src/types.ts

@@ -42,7 +42,8 @@ export type KnownProvider =
 	| "opencode-go"
 	| "kimi-coding"
 	| "cloudflare-workers-ai"
-	| "cloudflare-ai-gateway";
+	| "cloudflare-ai-gateway"
+	| "xiaomi";
 export type Provider = KnownProvider | string;
 
 export type ThinkingLevel = "minimal" | "low" | "medium" | "high" | "xhigh";

packages/ai/src/utils/overflow.ts

@@ -23,6 +23,9 @@ import type { AssistantMessage } from "../types.js";
  * - Cerebras: "400/413 status code (no body)"
  * - Mistral: "Prompt contains X tokens ... too large for model with Y maximum context length"
  * - z.ai: Does NOT error, accepts overflow silently - handled via usage.input > contextWindow
+ * - Xiaomi MiMo: Truncates input to fill contextWindow exactly, then returns finish_reason "length"
+ *   with output=0 (no room left to generate). Detected via stopReason "length" + zero output +
+ *   input filling the context window.
  * - Ollama: Some deployments truncate silently, others return errors like "prompt too long; exceeded max context length by X tokens"
  */
 const OVERFLOW_PATTERNS = [
@@ -90,6 +93,8 @@ const NON_OVERFLOW_PATTERNS = [
  * **Unreliable detection:**
  * - z.ai: Sometimes accepts overflow silently (detectable via usage.input > contextWindow),
  *   sometimes returns rate limit errors. Pass contextWindow param to detect silent overflow.
+ * - Xiaomi MiMo: Truncates input to fit contextWindow then returns stopReason "length" with
+ *   output=0. Pass contextWindow param to detect via the "filled context + zero output" signal.
  * - Ollama: May truncate input silently for some setups, but may also return explicit
  *   overflow errors that match the patterns above. Silent truncation still cannot be
  *   detected here because we do not know the expected token count.
@@ -127,6 +132,16 @@ export function isContextOverflow(message: AssistantMessage, contextWindow?: num
 		}
 	}
 
+	// Case 3: Length-stop overflow (Xiaomi MiMo style) - server truncates oversized input
+	// to fit the context window, leaving no room for output. Returns stopReason "length"
+	// with output=0 and input+cacheRead filling the context window.
+	if (contextWindow && message.stopReason === "length" && message.usage.output === 0) {
+		const inputTokens = message.usage.input + message.usage.cacheRead;
+		if (inputTokens >= contextWindow * 0.99) {
+			return true;
+		}
+	}
+
 	return false;
 }
 

packages/ai/test/abort.test.ts

@@ -190,6 +190,18 @@ describe("AI Providers Abort Tests", () => {
 		});
 	});
 
+	describe.skipIf(!process.env.XIAOMI_API_KEY)("Xiaomi MiMo Provider Abort", () => {
+		const llm = getModel("xiaomi", "mimo-v2.5-pro");
+
+		it("should abort mid-stream", { retry: 3 }, async () => {
+			await testAbortSignal(llm);
+		});
+
+		it("should handle immediate abort", { retry: 3 }, async () => {
+			await testImmediateAbort(llm);
+		});
+	});
+
 	describe.skipIf(!process.env.KIMI_API_KEY)("Kimi For Coding Provider Abort", () => {
 		const llm = getModel("kimi-coding", "kimi-k2-thinking");
 

packages/ai/test/context-overflow.test.ts

@@ -389,6 +389,25 @@ describe("Context overflow error handling", () => {
 		}, 120000);
 	});
 
+	// =============================================================================
+	// Xiaomi MiMo
+	// =============================================================================
+
+	describe.skipIf(!process.env.XIAOMI_API_KEY)("Xiaomi MiMo", () => {
+		// Xiaomi silently truncates oversized input to fill the context window exactly,
+		// then returns finish_reason "length" with output=0 (no room left to generate).
+		// This is a detectable overflow signal but uses stopReason "length" rather than "error".
+		it("mimo-v2.5-pro - should detect overflow via isContextOverflow", async () => {
+			const model = getModel("xiaomi", "mimo-v2.5-pro");
+			const result = await testContextOverflow(model, process.env.XIAOMI_API_KEY!);
+			logResult(result);
+
+			expect(result.stopReason).toBe("length");
+			expect(result.usage.output).toBe(0);
+			expect(isContextOverflow(result.response, model.contextWindow)).toBe(true);
+		}, 120000);
+	});
+
 	// =============================================================================
 	// Kimi For Coding
 	// =============================================================================

packages/ai/test/cross-provider-handoff.test.ts

@@ -113,6 +113,7 @@ const PROVIDER_MODEL_PAIRS: ProviderModelPair[] = [
 	{ provider: "mistral", model: "devstral-medium-latest", label: "mistral-devstral-medium" },
 	// MiniMax
 	{ provider: "minimax", model: "MiniMax-M2.7", label: "minimax-m2.7" },
+	{ provider: "minimax-cn", model: "MiniMax-M2.7", label: "minimax-m2.7" },
 	// OpenCode Zen
 	{ provider: "opencode", model: "big-pickle", label: "zen-big-pickle" },
 	{ provider: "opencode", model: "claude-sonnet-4-5", label: "zen-claude-sonnet-4-5" },
@@ -123,6 +124,8 @@ const PROVIDER_MODEL_PAIRS: ProviderModelPair[] = [
 	// OpenCode Go
 	{ provider: "opencode-go", model: "kimi-k2.5", label: "go-kimi-k2.5" },
 	{ provider: "opencode-go", model: "minimax-m2.5", label: "go-minimax-m2.5" },
+	// Xiaomi MiMo
+	{ provider: "xiaomi", model: "mimo-v2.5-pro", label: "xiaomi-mimo-v2.5-pro" },
 ];
 
 // Cached context structure

packages/ai/test/empty.test.ts

@@ -427,6 +427,26 @@ describe("AI Providers Empty Message Tests", () => {
 		});
 	});
 
+	describe.skipIf(!process.env.XIAOMI_API_KEY)("Xiaomi MiMo Provider Empty Messages", () => {
+		const llm = getModel("xiaomi", "mimo-v2.5-pro");
+
+		it("should handle empty content array", { retry: 3, timeout: 30000 }, async () => {
+			await testEmptyMessage(llm);
+		});
+
+		it("should handle empty string content", { retry: 3, timeout: 30000 }, async () => {
+			await testEmptyStringMessage(llm);
+		});
+
+		it("should handle whitespace-only content", { retry: 3, timeout: 30000 }, async () => {
+			await testWhitespaceOnlyMessage(llm);
+		});
+
+		it("should handle empty assistant message in conversation", { retry: 3, timeout: 30000 }, async () => {
+			await testEmptyAssistantMessage(llm);
+		});
+	});
+
 	describe.skipIf(!process.env.KIMI_API_KEY)("Kimi For Coding Provider Empty Messages", () => {
 		const llm = getModel("kimi-coding", "kimi-k2-thinking");
 

packages/ai/test/image-tool-result.test.ts

@@ -298,6 +298,18 @@ describe("Tool Results with Images", () => {
 		});
 	});
 
+	describe.skipIf(!process.env.XIAOMI_API_KEY)("Xiaomi MiMo Provider (mimo-v2.5-pro)", () => {
+		const llm = getModel("xiaomi", "mimo-v2.5-pro");
+
+		it("should handle tool result with only image", { retry: 3, timeout: 30000 }, async () => {
+			await handleToolWithImageResult(llm);
+		});
+
+		it("should handle tool result with text and image", { retry: 3, timeout: 30000 }, async () => {
+			await handleToolWithTextAndImageResult(llm);
+		});
+	});
+
 	describe.skipIf(!process.env.KIMI_API_KEY)("Kimi For Coding Provider (kimi-for-coding)", () => {
 		const llm = getModel("kimi-coding", "kimi-for-coding");
 

packages/ai/test/overflow.test.ts

@@ -61,4 +61,39 @@ describe("isContextOverflow", () => {
 		const message = createErrorMessage("Too many requests. Please slow down.");
 		expect(isContextOverflow(message, 200000)).toBe(false);
 	});
+
+	function createLengthStopMessage(input: number, cacheRead: number, output: number): AssistantMessage {
+		return {
+			role: "assistant",
+			content: [],
+			api: "openai-completions",
+			provider: "xiaomi",
+			model: "mimo-v2.5-pro",
+			usage: {
+				input,
+				output,
+				cacheRead,
+				cacheWrite: 0,
+				totalTokens: input + cacheRead + output,
+				cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0, total: 0 },
+			},
+			stopReason: "length",
+			timestamp: Date.now(),
+		};
+	}
+
+	it("detects Xiaomi-style overflow (length stop with zero output and filled context)", () => {
+		const message = createLengthStopMessage(58, 1048512, 0);
+		expect(isContextOverflow(message, 1048576)).toBe(true);
+	});
+
+	it("does not treat normal length stops with output as overflow", () => {
+		const message = createLengthStopMessage(1000, 0, 4096);
+		expect(isContextOverflow(message, 200000)).toBe(false);
+	});
+
+	it("does not treat length stops far below context as overflow", () => {
+		const message = createLengthStopMessage(100, 0, 0);
+		expect(isContextOverflow(message, 200000)).toBe(false);
+	});
 });

packages/ai/test/stream.test.ts

@@ -993,6 +993,24 @@ describe("Generate E2E Tests", () => {
 		},
 	);
 
+	describe.skipIf(!process.env.XIAOMI_API_KEY)(
+		"Xiaomi MiMo Provider (Xiaomi MiMo-V2.5-Pro via OpenAI Completions)",
+		() => {
+			const llm = getModel("xiaomi", "mimo-v2.5-pro");
+
+			it("should complete basic text generation", { retry: 3 }, async () => {
+				await basicTextGeneration(llm);
+			});
+
+			it("should handle tool calling", { retry: 3 }, async () => {
+				await handleToolCall(llm);
+			});
+
+			it("should handle streaming", { retry: 3 }, async () => {
+				await handleStreaming(llm);
+			});
+		},
+	);
 	// =========================================================================
 	// OAuth-based providers (credentials from ~/.pi/agent/oauth.json)
 	// Tokens are resolved at module level (see oauthTokens above)

packages/ai/test/tokens.test.ts

@@ -220,6 +220,14 @@ describe("Token Statistics on Abort", () => {
 		});
 	});
 
+	describe.skipIf(!process.env.XIAOMI_API_KEY)("Xiaomi MiMo Provider", () => {
+		const llm = getModel("xiaomi", "mimo-v2.5-pro");
+
+		it("should include token stats when aborted mid-stream", { retry: 3, timeout: 30000 }, async () => {
+			await testTokensOnAbort(llm);
+		});
+	});
+
 	// =========================================================================
 	// OAuth-based providers (credentials from ~/.pi/agent/oauth.json)
 	// =========================================================================

packages/ai/test/tool-call-without-result.test.ts

@@ -215,6 +215,14 @@ describe("Tool Call Without Result Tests", () => {
 		});
 	});
 
+	describe.skipIf(!process.env.XIAOMI_API_KEY)("Xiaomi MiMo Provider", () => {
+		const model = getModel("xiaomi", "mimo-v2.5-pro");
+
+		it("should filter out tool calls without corresponding tool results", { retry: 3, timeout: 30000 }, async () => {
+			await testToolCallWithoutResult(model);
+		});
+	});
+
 	describe.skipIf(!process.env.KIMI_API_KEY)("Kimi For Coding Provider", () => {
 		const model = getModel("kimi-coding", "kimi-k2-thinking");
 

packages/ai/test/total-tokens.test.ts

@@ -443,6 +443,29 @@ describe("totalTokens field", () => {
 		);
 	});
 
+	// =========================================================================
+	// Xiaomi MiMo
+	// =========================================================================
+
+	describe.skipIf(!process.env.XIAOMI_API_KEY)("Xiaomi MiMo", () => {
+		it(
+			"mimo-v2.5-pro - should return totalTokens equal to sum of components",
+			{ retry: 3, timeout: 60000 },
+			async () => {
+				const llm = getModel("xiaomi", "mimo-v2.5-pro");
+
+				console.log(`\nXiaomi MiMo / ${llm.id}:`);
+				const { first, second } = await testTotalTokensWithCache(llm, { apiKey: process.env.XIAOMI_API_KEY });
+
+				logUsage("First request", first);
+				logUsage("Second request", second);
+
+				assertTotalTokensEqualsComponents(first);
+				assertTotalTokensEqualsComponents(second);
+			},
+		);
+	});
+
 	// =========================================================================
 	// Kimi For Coding
 	// =========================================================================

packages/ai/test/unicode-surrogate.test.ts

@@ -594,6 +594,22 @@ describe("AI Providers Unicode Surrogate Pair Tests", () => {
 		});
 	});
 
+	describe.skipIf(!process.env.XIAOMI_API_KEY)("Xiaomi MiMo Provider Unicode Handling", () => {
+		const llm = getModel("xiaomi", "mimo-v2.5-pro");
+
+		it("should handle emoji in tool results", { retry: 3, timeout: 30000 }, async () => {
+			await testEmojiInToolResults(llm);
+		});
+
+		it("should handle real-world LinkedIn comment data with emoji", { retry: 3, timeout: 30000 }, async () => {
+			await testRealWorldLinkedInData(llm);
+		});
+
+		it("should handle unpaired high surrogate (0xD83D) in tool results", { retry: 3, timeout: 30000 }, async () => {
+			await testUnpairedHighSurrogate(llm);
+		});
+	});
+
 	describe.skipIf(!process.env.KIMI_API_KEY)("Kimi For Coding Provider Unicode Handling", () => {
 		const llm = getModel("kimi-coding", "kimi-k2-thinking");
 

packages/coding-agent/README.md

@@ -128,6 +128,7 @@ For each built-in provider, pi maintains a list of tool-capable models, updated
 - Fireworks
 - Kimi For Coding
 - MiniMax
+- Xiaomi MiMo
 
 See [docs/providers.md](docs/providers.md) for detailed setup instructions.
 

packages/coding-agent/docs/providers.md

@@ -69,6 +69,7 @@ pi
 | Kimi For Coding | `KIMI_API_KEY` | `kimi-coding` |
 | MiniMax | `MINIMAX_API_KEY` | `minimax` |
 | MiniMax (China) | `MINIMAX_CN_API_KEY` | `minimax-cn` |
+| Xiaomi MiMo | `XIAOMI_API_KEY` | `xiaomi` |
 
 Reference for environment variables and `auth.json` keys: [`const envMap`](https://github.com/badlogic/pi-mono/blob/main/packages/ai/src/env-api-keys.ts) in [`packages/ai/src/env-api-keys.ts`](https://github.com/badlogic/pi-mono/blob/main/packages/ai/src/env-api-keys.ts).
 
@@ -83,7 +84,8 @@ Store credentials in `~/.pi/agent/auth.json`:
   "deepseek": { "type": "api_key", "key": "sk-..." },
   "google": { "type": "api_key", "key": "..." },
   "opencode": { "type": "api_key", "key": "..." },
-  "opencode-go": { "type": "api_key", "key": "..." }
+  "opencode-go": { "type": "api_key", "key": "..." },
+  "xiaomi": { "type": "api_key", "key": "..." }
 }
 ```
 

packages/coding-agent/src/cli/args.ts

@@ -320,6 +320,7 @@ ${chalk.bold("Environment Variables:")}
   CLOUDFLARE_API_KEY               - Cloudflare API token (Workers AI and AI Gateway)
   CLOUDFLARE_ACCOUNT_ID            - Cloudflare account id (required for both)
   CLOUDFLARE_GATEWAY_ID            - Cloudflare AI Gateway slug (required for AI Gateway)
+  XIAOMI_API_KEY                   - Xiaomi MiMo API key
   AWS_PROFILE                      - AWS profile for Amazon Bedrock
   AWS_ACCESS_KEY_ID                - AWS access key for Amazon Bedrock
   AWS_SECRET_ACCESS_KEY            - AWS secret key for Amazon Bedrock

packages/coding-agent/src/core/model-resolver.ts

@@ -39,6 +39,7 @@ export const defaultModelPerProvider: Record<KnownProvider, string> = {
 	"kimi-coding": "kimi-for-coding",
 	"cloudflare-workers-ai": "@cf/moonshotai/kimi-k2.6",
 	"cloudflare-ai-gateway": "workers-ai/@cf/moonshotai/kimi-k2.6",
+	xiaomi: "mimo-v2.5-pro",
 };
 
 export interface ScopedModel {

packages/coding-agent/src/core/provider-display-names.ts

@@ -24,4 +24,5 @@ export const BUILT_IN_PROVIDER_DISPLAY_NAMES: Record<string, string> = {
 	"vercel-ai-gateway": "Vercel AI Gateway",
 	xai: "xAI",
 	zai: "ZAI",
+	xiaomi: "Xiaomi MiMo",
 };