fix(openai): preserve reasoning for local OpenAI-compatible models via R1 toggle

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

@@ -837,6 +837,20 @@ describe("OpenAiHandler", () => {
 			expect(model.id).toBe("")
 			expect(model.info).toBeDefined()
 		})
+
+		it("should set preserveReasoning when openAiR1FormatEnabled is on", () => {
+			const r1Handler = new OpenAiHandler({
+				...mockOptions,
+				openAiR1FormatEnabled: true,
+			})
+			const model = r1Handler.getModel()
+			expect(model.info.preserveReasoning).toBe(true)
+		})
+
+		it("should not set preserveReasoning by default", () => {
+			const model = handler.getModel()
+			expect(model.info.preserveReasoning).toBeUndefined()
+		})
 	})
 
 	describe("Azure AI Inference Service", () => {

src/api/providers/openai.ts

@@ -293,7 +293,15 @@ export class OpenAiHandler extends BaseProvider implements SingleCompletionHandl
 			settings: this.options,
 			defaultTemperature: 0,
 		})
-		return { id, info, ...params }
+		// Local OpenAI-compatible reasoning models (llama.cpp, LM Studio, Ollama)
+		// stream reasoning_content, but Roo strips it from the follow-up context
+		// unless info.preserveReasoning is set. When the user enables the R1 format
+		// toggle, treat the model as preserving reasoning so the chain is fed back.
+		return {
+			id,
+			info: this.options.openAiR1FormatEnabled ? { ...info, preserveReasoning: true } : info,
+			...params,
+		}
 	}
 
 	async completePrompt(prompt: string, options?: CompletePromptOptions): Promise<string> {