feat: enable image support for DeepSeek V4 models (#963)

DeepSeek V4 Pro and V4 Flash support image inputs via their OpenAI-compatible
API, but the model definitions had supportsImages: false. This change flips it
to true for both models, enabling users to attach images when using these models.

Author: grizmin

packages/types/src/providers/deepseek.ts

@@ -12,7 +12,7 @@ export const deepSeekModels = {
 	"deepseek-v4-flash": {
 		maxTokens: 384_000,
 		contextWindow: 1_000_000,
-		supportsImages: false,
+		supportsImages: true,
 		supportsPromptCache: true,
 		supportsReasoningEffort: ["disable", "low", "medium", "high", "xhigh"],
 		preserveReasoning: true,
@@ -26,7 +26,7 @@ export const deepSeekModels = {
 	"deepseek-v4-pro": {
 		maxTokens: 384_000,
 		contextWindow: 1_000_000,
-		supportsImages: false,
+		supportsImages: true,
 		supportsPromptCache: true,
 		supportsReasoningEffort: ["disable", "low", "medium", "high", "xhigh"],
 		preserveReasoning: true,

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

@@ -225,6 +225,7 @@ describe("DeepSeekHandler", () => {
 			expect(model.id).toBe("deepseek-v4-flash")
 			expect(model.info.maxTokens).toBe(384_000)
 			expect(model.info.contextWindow).toBe(1_000_000)
+			expect(model.info.supportsImages).toBe(true)
 			expect((model.info as ModelInfo).supportsReasoningEffort).toContain("xhigh")
 		})
 
@@ -252,6 +253,7 @@ describe("DeepSeekHandler", () => {
 			expect(model.info).toBeDefined()
 			expect(model.info.maxTokens).toBe(384_000)
 			expect(model.info.contextWindow).toBe(1_000_000)
+			expect(model.info.supportsImages).toBe(true)
 			expect(model.info.supportsPromptCache).toBe(true)
 			expect((model.info as ModelInfo).preserveReasoning).toBe(true)
 			expect((model.info as ModelInfo).reasoningEffort).toBe("high")