openclaw/docs/concepts/retry.md at a0ad38e71ab727a269679bce096191d50cdffedc

mirror of https://github.com/openclaw/openclaw.git synced 2026-08-12 21:53:00 -06:00

Files

T

Peter Steinberger a0ad38e71a feat(docs-ci): validate docs config examples against the schema (#121336 )

* feat(docs-ci): validate config examples against schema

* docs: teach canonical agent roster configuration

* docs: nest inline environment variables under vars

* docs: update canonical media model keys

* docs: remove retired config keys from examples

* fix(docs-ci): keep audit internals private

* feat(docs-ci): validate plugin-owned config examples

* fix(docs-ci): validate indented config fences

* fix(ci): route manifest changes through docs audit

* chore(docs): refresh generated config baselines

2026-08-10 07:57:56 -07:00

2.1 KiB

Raw Blame History

summary, read_when, title

summary

read_when

title

Retry policy for outbound provider calls

Updating provider retry behavior or defaults

Debugging provider send errors or rate limits

Retry policy

Goals

Retry per HTTP request, not per multi-step flow.
Preserve ordering by retrying only the current step.
Avoid duplicating non-idempotent operations.

Defaults

Setting	Default
Attempts	3
Max delay cap	30000 ms
Jitter	0.1 (10%)
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, and 5xx) can include retry-after-ms or retry-after. When that wait is longer than 60 seconds, OpenClaw injects x-should-retry: false so 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 to 0, false, off, none, or disabled to let SDKs honor long Retry-After sleeps internally.

Discord

Retries on rate-limit errors (HTTP 429), request timeouts, HTTP 5xx responses, and transient transport failures such as DNS lookup failures, connection resets, socket closes, and fetch failures.
Uses Discord retry_after when available, otherwise exponential backoff.

Retries on transient errors (429, timeout, connect/reset/closed, temporarily unavailable).
Uses retry_after when available, otherwise exponential backoff.
HTML/Markdown parse errors are not retried; they fall back to plain text on the first attempt.

Configuration

Discord and Telegram channel retry timings are built in and are not configurable in openclaw.json.

Notes

Retries apply per request (message send, media upload, reaction, poll, sticker).
Composite flows do not retry completed steps.

2.1 KiB Raw Blame History