fix: use default maxTokens values instead of maximum for DeepSeek models

- deepseek-chat: 4096 (4K default) instead of 8192 (8K max)
- deepseek-reasoner: 32768 (32K default) instead of 65536 (64K max)
- Updated tests to match new default values
- Updated description to clarify default vs max output tokens

Author: daniel-lxs

packages/types/src/providers/deepseek.ts

@@ -7,7 +7,7 @@ export const deepSeekDefaultModelId: DeepSeekModelId = "deepseek-chat"
 
 export const deepSeekModels = {
 	"deepseek-chat": {
-		maxTokens: 8192,
+		maxTokens: 4096, // Default 4K, max 8K
 		contextWindow: 128_000,
 		supportsImages: false,
 		supportsPromptCache: true,
@@ -18,15 +18,15 @@ export const deepSeekModels = {
 		description: `DeepSeek-V3 achieves a significant breakthrough in inference speed over previous models. It tops the leaderboard among open-source models and rivals the most advanced closed-source models globally.`,
 	},
 	"deepseek-reasoner": {
-		maxTokens: 65536, // 64K max output for reasoning mode
+		maxTokens: 32768, // Default 32K, max 64K for reasoning mode
 		contextWindow: 128_000,
 		supportsImages: false,
 		supportsPromptCache: true,
 		inputPrice: 0.55, // $0.55 per million tokens (cache miss)
 		outputPrice: 2.19, // $2.19 per million tokens
 		cacheWritesPrice: 0.55, // $0.55 per million tokens (cache miss)
 		cacheReadsPrice: 0.14, // $0.14 per million tokens (cache hit)
-		description: `DeepSeek-R1 achieves performance comparable to OpenAI-o1 across math, code, and reasoning tasks. Supports Chain of Thought reasoning with up to 64K output tokens.`,
+		description: `DeepSeek-R1 achieves performance comparable to OpenAI-o1 across math, code, and reasoning tasks. Supports Chain of Thought reasoning with default 32K output tokens (max 64K).`,
 	},
 } as const satisfies Record<string, ModelInfo>
 

src/api/providers/__tests__/deepseek.spec.ts

@@ -154,7 +154,7 @@ describe("DeepSeekHandler", () => {
 			const model = handler.getModel()
 			expect(model.id).toBe(mockOptions.apiModelId)
 			expect(model.info).toBeDefined()
-			expect(model.info.maxTokens).toBe(8192) // deepseek-chat has 8K max
+			expect(model.info.maxTokens).toBe(4096) // deepseek-chat default is 4K (max 8K)
 			expect(model.info.contextWindow).toBe(128_000)
 			expect(model.info.supportsImages).toBe(false)
 			expect(model.info.supportsPromptCache).toBe(true) // Should be true now
@@ -168,7 +168,7 @@ describe("DeepSeekHandler", () => {
 			const model = handlerWithReasoner.getModel()
 			expect(model.id).toBe("deepseek-reasoner")
 			expect(model.info).toBeDefined()
-			expect(model.info.maxTokens).toBe(65536) // deepseek-reasoner has 64K max
+			expect(model.info.maxTokens).toBe(32768) // deepseek-reasoner default is 32K (max 64K)
 			expect(model.info.contextWindow).toBe(128_000)
 			expect(model.info.supportsImages).toBe(false)
 			expect(model.info.supportsPromptCache).toBe(true)