siyuan-note/siyuan · error

model request timeout

Error message

model request timeout

What it means

errModelRequestTimeout is a sentinel error indicating the HTTP request to the model provider exceeded the configured request timeout. createStreamWithRetry maps a timer expiration onto this sentinel (optionally overriding the transport error) and classifyRetry labels it "timeout" so the retry logic can back off and retry.

Source

Thrown at kernel/agent/agent.go:2444

			}
			e := SessionEntry{
				ID:                   id,
				Type:                 "assistant",
				Content:              m.Content,
				ReasoningCont:        m.ReasoningContent,
				ResponseOutput:       util.CloneOpenAIResponseOutput(m.ResponseOutput),
				ResponseOutputTokens: m.ResponseOutputTokens,
				RoundID:              m.RoundID,
				ToolCalls:            m.ToolCalls,
			}
			entries = append(entries, e)
		}
	}
	return entries
}

var (
	errModelRequestTimeout    = errors.New("model request timeout")
	errModelStreamIdleTimeout = errors.New("model stream idle timeout")
)

func createStreamWithRetry(ctx context.Context, client *openai.Client, req openai.ChatCompletionRequest, maxRetries int,
	requestTimeout, streamIdleTimeout time.Duration, retryDelay func(string, int) time.Duration,
	ch chan<- AgentEvent) (*util.OpenAICompletionStream, openai.ChatCompletionStreamResponse, context.CancelFunc, error) {
	return createProtocolStreamWithRetry(ctx, client, util.OpenAIProtocolChatCompletions, req, nil, maxRetries,
		requestTimeout, streamIdleTimeout, retryDelay, ch)
}

func createProtocolStreamWithRetry(ctx context.Context, client *openai.Client, protocol string,
	req openai.ChatCompletionRequest, responseInput []any, maxRetries int, requestTimeout, streamIdleTimeout time.Duration,
	retryDelay func(string, int) time.Duration,
	ch chan<- AgentEvent) (*util.OpenAICompletionStream, openai.ChatCompletionStreamResponse, context.CancelFunc, error) {
	if maxRetries < 0 {
		maxRetries = 0
	}

View on GitHub (pinned to 8641553a1f)

Solutions

1. Increase the model request timeout configuration
2. Check provider status/network connectivity and proxy settings
3. Retry — the built-in retry loop already classifies this as retryable ("timeout")
4. Reduce prompt size so the request completes within the timeout
5. Verify maxRetries is not 0 if automatic retries are desired

if errors.Is(err, errModelRequestTimeout) {
    // back off and retry; also consider raising the request timeout
}

When it happens

Trigger: In createStreamWithRetry/createProtocolStreamWithRetry, the per-request context timer fires before the stream is established (requestTimedOut is true), so err is replaced with errModelRequestTimeout; also returned by createResponseCompaction and covered by TestCreateStreamRequestTimeoutAndZeroRetries.

Common situations: Slow or overloaded model provider endpoints; requestTimeout configured too aggressively low; network latency/proxy delays; very large prompts taking longer than the timeout to be accepted.

Understand the failure class

Background: Request timed out: what client-side request timeouts mean across libraries (Request timed out, TIMED_OUT, APITimeoutError) — this error's family across 39 libraries.

• Timeouts: ETIMEDOUT, deadlines, and hung requests — what actually expires when a request times out.

Related errors

• model stream idle timeout
• read body failed: %s
• host has no public IP:
• compaction summary request failed: %w
• compaction summary stream failed: %w

AI-assisted analysis of siyuan-note/siyuan@8641553a1f (2026-09-11). Data as JSON: /api/errors/e704236803979d36. Report an issue: GitHub.