Documentation Index
Fetch the complete documentation index at: https://docs.openclaw.ai/llms.txt
Use this file to discover all available pages before exploring further.
Goals
- Retry per HTTP request, not per multi-step flow.
- Preserve ordering by retrying only the current step.
- Avoid duplicating non-idempotent operations.
Defaults
- Attempts: 3
- Max delay cap: 30000 ms
- Jitter: 0.1 (10 percent)
- Provider defaults:
- Telegram min delay: 400 ms
- Discord min delay: 500 ms
Behavior
Model providers
- OpenClaw lets provider SDKs handle normal short retries.
- For Stainless-based SDKs such as Anthropic and OpenAI, retryable responses
(
408,409,429, and5xx) can includeretry-after-msorretry-after. When that wait is longer than 60 seconds, OpenClaw injectsx-should-retry: falseso the SDK surfaces the error immediately and model failover can rotate to another auth profile or fallback model. - Override the cap with
OPENCLAW_SDK_RETRY_MAX_WAIT_SECONDS=<seconds>. Set it to0,false,off,none, ordisabledto let SDKs honor longRetry-Aftersleeps internally.
Discord
- Retries only on rate-limit errors (HTTP 429).
- Uses Discord
retry_afterwhen available, otherwise exponential backoff.
Telegram
- Retries on transient errors (429, timeout, connect/reset/closed, temporarily unavailable).
- Uses
retry_afterwhen available, otherwise exponential backoff. - Markdown parse errors are not retried; they fall back to plain text.
Configuration
Set retry policy per provider in~/.openclaw/openclaw.json:
Notes
- Retries apply per request (message send, media upload, reaction, poll, sticker).
- Composite flows do not retry completed steps.