fix: calculate LM Studio maxTokens as 20% of context window

- Fix context limit crash issue by properly calculating maxTokens
- Previously maxTokens was set equal to contextWindow causing overflow
- Now maxTokens is calculated as 20% of contextWindow to leave room for input
- Add test coverage for the new calculation logic

Fixes #7388

src/api/providers/fetchers/__tests__/lmstudio.test.ts

@@ -60,7 +60,7 @@ describe("LMStudio Fetcher", () => {
 				supportsPromptCache: true,
 				supportsImages: rawModel.vision,
 				supportsComputerUse: false,
-				maxTokens: rawModel.contextLength,
+				maxTokens: Math.ceil(rawModel.contextLength * 0.2), // Should be 20% of context window
 				inputPrice: 0,
 				outputPrice: 0,
 				cacheWritesPrice: 0,
@@ -70,6 +70,36 @@ describe("LMStudio Fetcher", () => {
 			const result = parseLMStudioModel(rawModel)
 			expect(result).toEqual(expectedModelInfo)
 		})
+
+		it("should calculate maxTokens as 20% of context window", () => {
+			const testCases = [
+				{ contextLength: 8192, expectedMaxTokens: Math.ceil(8192 * 0.2) }, // 1639
+				{ contextLength: 128000, expectedMaxTokens: Math.ceil(128000 * 0.2) }, // 25600
+				{ contextLength: 200000, expectedMaxTokens: Math.ceil(200000 * 0.2) }, // 40000
+			]
+
+			testCases.forEach(({ contextLength, expectedMaxTokens }) => {
+				const rawModel: LLMInstanceInfo = {
+					type: "llm",
+					modelKey: "test-model",
+					format: "safetensors",
+					displayName: "Test Model",
+					path: "test/model",
+					sizeBytes: 1000000,
+					architecture: "test",
+					identifier: "test/model",
+					instanceReference: "TEST123",
+					vision: false,
+					trainedForToolUse: false,
+					maxContextLength: contextLength,
+					contextLength: contextLength,
+				}
+
+				const result = parseLMStudioModel(rawModel)
+				expect(result.maxTokens).toBe(expectedMaxTokens)
+				expect(result.contextWindow).toBe(contextLength)
+			})
+		})
 	})
 
 	describe("getLMStudioModels", () => {

src/api/providers/fetchers/lmstudio.ts

@@ -38,13 +38,18 @@ export const parseLMStudioModel = (rawModel: LLMInstanceInfo | LLMInfo): ModelIn
 	// Handle both LLMInstanceInfo (from loaded models) and LLMInfo (from downloaded models)
 	const contextLength = "contextLength" in rawModel ? rawModel.contextLength : rawModel.maxContextLength
 
+	// Calculate maxTokens as 20% of context window to prevent context overflow
+	// This ensures there's always room for input tokens and prevents crashes
+	// when approaching the context limit
+	const maxOutputTokens = Math.ceil(contextLength * 0.2)
+
 	const modelInfo: ModelInfo = Object.assign({}, lMStudioDefaultModelInfo, {
 		description: `${rawModel.displayName} - ${rawModel.path}`,
 		contextWindow: contextLength,
 		supportsPromptCache: true,
 		supportsImages: rawModel.vision,
 		supportsComputerUse: false,
-		maxTokens: contextLength,
+		maxTokens: maxOutputTokens,
 	})
 
 	return modelInfo