feat(ai): add Kimi For Coding provider support

- Add kimi-coding provider using Anthropic Messages API
- API endpoint: https://api.kimi.com/coding/v1
- Environment variable: KIMI_API_KEY
- Models: kimi-k2-thinking (text), k2p5 (text + image)
- Add context overflow detection pattern for Kimi errors
- Add tests for all standard test suites

packages/ai/test/abort.test.ts

@@ -193,6 +193,18 @@ describe("AI Providers Abort Tests", () => {
 		});
 	});
 
+	describe.skipIf(!process.env.KIMI_API_KEY)("Kimi For Coding Provider Abort", () => {
+		const llm = getModel("kimi-coding", "kimi-k2-thinking");
+
+		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.AI_GATEWAY_API_KEY)("Vercel AI Gateway Provider Abort", () => {
 		const llm = getModel("vercel-ai-gateway", "google/gemini-2.5-flash");
 

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

@@ -443,6 +443,21 @@ describe("Context overflow error handling", () => {
 		}, 120000);
 	});
 
+	// =============================================================================
+	// Kimi For Coding
+	// =============================================================================
+
+	describe.skipIf(!process.env.KIMI_API_KEY)("Kimi For Coding", () => {
+		it("kimi-k2-thinking - should detect overflow via isContextOverflow", async () => {
+			const model = getModel("kimi-coding", "kimi-k2-thinking");
+			const result = await testContextOverflow(model, process.env.KIMI_API_KEY!);
+			logResult(result);
+
+			expect(result.stopReason).toBe("error");
+			expect(isContextOverflow(result.response, model.contextWindow)).toBe(true);
+		}, 120000);
+	});
+
 	// =============================================================================
 	// Vercel AI Gateway - Unified API for multiple providers
 	// =============================================================================

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

@@ -88,6 +88,8 @@ const PROVIDER_MODEL_PAIRS: ProviderModelPair[] = [
 	{ provider: "groq", model: "openai/gpt-oss-120b", label: "groq-gpt-oss-120b" },
 	// Hugging Face
 	{ provider: "huggingface", model: "moonshotai/Kimi-K2.5", label: "huggingface-kimi-k2.5" },
+	// Kimi For Coding
+	{ provider: "kimi-coding", model: "kimi-k2-thinking", label: "kimi-coding-k2-thinking" },
 	// Mistral
 	{ provider: "mistral", model: "devstral-medium-latest", label: "mistral-devstral-medium" },
 	// MiniMax

packages/ai/test/empty.test.ts

@@ -388,6 +388,26 @@ describe("AI Providers Empty Message Tests", () => {
 		});
 	});
 
+	describe.skipIf(!process.env.KIMI_API_KEY)("Kimi For Coding Provider Empty Messages", () => {
+		const llm = getModel("kimi-coding", "kimi-k2-thinking");
+
+		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.AI_GATEWAY_API_KEY)("Vercel AI Gateway Provider Empty Messages", () => {
 		const llm = getModel("vercel-ai-gateway", "google/gemini-2.5-flash");
 

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

@@ -300,6 +300,18 @@ describe("Tool Results with Images", () => {
 		});
 	});
 
+	describe.skipIf(!process.env.KIMI_API_KEY)("Kimi For Coding Provider (k2p5)", () => {
+		const llm = getModel("kimi-coding", "k2p5");
+
+		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.AI_GATEWAY_API_KEY)("Vercel AI Gateway Provider (google/gemini-2.5-flash)", () => {
 		const llm = getModel("vercel-ai-gateway", "google/gemini-2.5-flash");
 

packages/ai/test/stream.test.ts

@@ -862,6 +862,33 @@ describe("Generate E2E Tests", () => {
 		});
 	});
 
+	describe.skipIf(!process.env.KIMI_API_KEY)(
+		"Kimi For Coding Provider (kimi-k2-thinking via Anthropic Messages)",
+		() => {
+			const llm = getModel("kimi-coding", "kimi-k2-thinking");
+
+			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);
+			});
+
+			it("should handle thinking mode", { retry: 3 }, async () => {
+				await handleThinking(llm, { thinkingEnabled: true, thinkingBudgetTokens: 2048 });
+			});
+
+			it("should handle multi-turn with thinking and tools", { retry: 3 }, async () => {
+				await multiTurn(llm, { thinkingEnabled: true, thinkingBudgetTokens: 2048 });
+			});
+		},
+	);
+
 	// =========================================================================
 	// OAuth-based providers (credentials from ~/.pi/agent/oauth.json)
 	// Tokens are resolved at module level (see oauthTokens above)

packages/ai/test/tokens.test.ts

@@ -186,6 +186,14 @@ describe("Token Statistics on Abort", () => {
 		});
 	});
 
+	describe.skipIf(!process.env.KIMI_API_KEY)("Kimi For Coding Provider", () => {
+		const llm = getModel("kimi-coding", "kimi-k2-thinking");
+
+		it("should include token stats when aborted mid-stream", { retry: 3, timeout: 30000 }, async () => {
+			await testTokensOnAbort(llm);
+		});
+	});
+
 	describe.skipIf(!process.env.AI_GATEWAY_API_KEY)("Vercel AI Gateway Provider", () => {
 		const llm = getModel("vercel-ai-gateway", "google/gemini-2.5-flash");
 

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

@@ -200,6 +200,14 @@ describe("Tool Call Without Result Tests", () => {
 		});
 	});
 
+	describe.skipIf(!process.env.KIMI_API_KEY)("Kimi For Coding Provider", () => {
+		const model = getModel("kimi-coding", "kimi-k2-thinking");
+
+		it("should filter out tool calls without corresponding tool results", { retry: 3, timeout: 30000 }, async () => {
+			await testToolCallWithoutResult(model);
+		});
+	});
+
 	describe.skipIf(!process.env.AI_GATEWAY_API_KEY)("Vercel AI Gateway Provider", () => {
 		const model = getModel("vercel-ai-gateway", "google/gemini-2.5-flash");
 

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

@@ -394,6 +394,29 @@ describe("totalTokens field", () => {
 		);
 	});
 
+	// =========================================================================
+	// Kimi For Coding
+	// =========================================================================
+
+	describe.skipIf(!process.env.KIMI_API_KEY)("Kimi For Coding", () => {
+		it(
+			"kimi-k2-thinking - should return totalTokens equal to sum of components",
+			{ retry: 3, timeout: 60000 },
+			async () => {
+				const llm = getModel("kimi-coding", "kimi-k2-thinking");
+
+				console.log(`\nKimi For Coding / ${llm.id}:`);
+				const { first, second } = await testTotalTokensWithCache(llm, { apiKey: process.env.KIMI_API_KEY });
+
+				logUsage("First request", first);
+				logUsage("Second request", second);
+
+				assertTotalTokensEqualsComponents(first);
+				assertTotalTokensEqualsComponents(second);
+			},
+		);
+	});
+
 	// =========================================================================
 	// Vercel AI Gateway
 	// =========================================================================

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

@@ -675,6 +675,22 @@ describe("AI Providers Unicode Surrogate Pair Tests", () => {
 		});
 	});
 
+	describe.skipIf(!process.env.KIMI_API_KEY)("Kimi For Coding Provider Unicode Handling", () => {
+		const llm = getModel("kimi-coding", "kimi-k2-thinking");
+
+		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.AI_GATEWAY_API_KEY)("Vercel AI Gateway Provider Unicode Handling", () => {
 		const llm = getModel("vercel-ai-gateway", "google/gemini-2.5-flash");