fix(ai,coding-agent): expose provider timeout/retry controls closes #3627

packages/ai/CHANGELOG.md

@@ -10,6 +10,7 @@
 
 - Fixed DeepSeek V4 session replay 400 errors by adding `thinkingFormat: "deepseek"` (sends `thinking: { type }` + `reasoning_effort`), a `reasoningEffortMap`, and `requiresReasoningContentOnAssistantMessages` compat that injects empty `reasoning_content` on all replayed assistant messages when reasoning is enabled ([#3636](https://github.com/badlogic/pi-mono/issues/3636))
 - Fixed GPT-5.5 generated context window metadata to use the observed 272k limit.
+- Fixed provider request controls to expose `timeoutMs` and `maxRetries` in stream options and forward them through OpenAI/Azure/Anthropic request options, preventing unconfigurable SDK timeout/retry defaults on long-running local inference requests ([#3627](https://github.com/badlogic/pi-mono/issues/3627))
 
 ## [0.70.0] - 2026-04-23
 

packages/ai/src/providers/anthropic.ts

@@ -457,7 +457,14 @@ export const streamAnthropic: StreamFunction<"anthropic-messages", AnthropicOpti
 				params = nextParams as MessageCreateParamsStreaming;
 			}
 			const response = await client.messages
-				.create({ ...params, stream: true }, { signal: options?.signal })
+				.create(
+					{ ...params, stream: true },
+					{
+						signal: options?.signal,
+						timeout: options?.timeoutMs,
+						maxRetries: options?.maxRetries,
+					},
+				)
 				.asResponse();
 			await options?.onResponse?.({ status: response.status, headers: headersToRecord(response.headers) }, model);
 			stream.push({ type: "start", partial: output });

packages/ai/src/providers/azure-openai-responses.ts

@@ -92,7 +92,11 @@ export const streamAzureOpenAIResponses: StreamFunction<"azure-openai-responses"
 				params = nextParams as ResponseCreateParamsStreaming;
 			}
 			const { data: openaiStream, response } = await client.responses
-				.create(params, options?.signal ? { signal: options.signal } : undefined)
+				.create(params, {
+					signal: options?.signal,
+					timeout: options?.timeoutMs,
+					maxRetries: options?.maxRetries,
+				})
 				.withResponse();
 			await options?.onResponse?.({ status: response.status, headers: headersToRecord(response.headers) }, model);
 			stream.push({ type: "start", partial: output });

packages/ai/src/providers/openai-completions.ts

@@ -145,7 +145,11 @@ export const streamOpenAICompletions: StreamFunction<"openai-completions", OpenA
 				params = nextParams as OpenAI.Chat.Completions.ChatCompletionCreateParamsStreaming;
 			}
 			const { data: openaiStream, response } = await client.chat.completions
-				.create(params, { signal: options?.signal })
+				.create(params, {
+					signal: options?.signal,
+					timeout: options?.timeoutMs,
+					maxRetries: options?.maxRetries,
+				})
 				.withResponse();
 			await options?.onResponse?.({ status: response.status, headers: headersToRecord(response.headers) }, model);
 			stream.push({ type: "start", partial: output });

packages/ai/src/providers/openai-responses.ts

@@ -99,7 +99,11 @@ export const streamOpenAIResponses: StreamFunction<"openai-responses", OpenAIRes
 				params = nextParams as ResponseCreateParamsStreaming;
 			}
 			const { data: openaiStream, response } = await client.responses
-				.create(params, options?.signal ? { signal: options.signal } : undefined)
+				.create(params, {
+					signal: options?.signal,
+					timeout: options?.timeoutMs,
+					maxRetries: options?.maxRetries,
+				})
 				.withResponse();
 			await options?.onResponse?.({ status: response.status, headers: headersToRecord(response.headers) }, model);
 			stream.push({ type: "start", partial: output });

packages/ai/src/providers/simple-options.ts

@@ -11,6 +11,8 @@ export function buildBaseOptions(model: Model<Api>, options?: SimpleStreamOption
 		headers: options?.headers,
 		onPayload: options?.onPayload,
 		onResponse: options?.onResponse,
+		timeoutMs: options?.timeoutMs,
+		maxRetries: options?.maxRetries,
 		maxRetryDelayMs: options?.maxRetryDelayMs,
 		metadata: options?.metadata,
 	};

packages/ai/src/types.ts

@@ -101,6 +101,16 @@ export interface StreamOptions {
 	 * Not supported by all providers (e.g., AWS Bedrock uses SDK auth).
 	 */
 	headers?: Record<string, string>;
+	/**
+	 * HTTP request timeout in milliseconds for providers/SDKs that support it.
+	 * For example, OpenAI and Anthropic SDK clients default to 10 minutes.
+	 */
+	timeoutMs?: number;
+	/**
+	 * Maximum retry attempts for providers/SDKs that support client-side retries.
+	 * For example, OpenAI and Anthropic SDK clients default to 2.
+	 */
+	maxRetries?: number;
 	/**
 	 * Maximum delay in milliseconds to wait for a retry when the server requests a long wait.
 	 * If the server's requested delay exceeds this value, the request fails immediately