forked from Selig/openclaw-skill
Selig
4c966a3ad2
6 custom skills (assign-task, dispatch-webhook, daily-briefing, task-capture, qmd-brain, tts-voice) with technical documentation. Compatible with Claude Code, OpenClaw, Codex CLI, and OpenCode.
44 lines
1.6 KiB
JSON
Executable File
44 lines
1.6 KiB
JSON
Executable File
{
|
|
"title": "Retry policy",
|
|
"content": "* Retry per HTTP request, not per multi-step flow.\n* Preserve ordering by retrying only the current step.\n* Avoid duplicating non-idempotent operations.\n\n* Attempts: 3\n* Max delay cap: 30000 ms\n* Jitter: 0.1 (10 percent)\n* Provider defaults:\n * Telegram min delay: 400 ms\n * Discord min delay: 500 ms\n\n* Retries only on rate-limit errors (HTTP 429).\n* Uses Discord `retry_after` when available, otherwise exponential backoff.\n\n* Retries on transient errors (429, timeout, connect/reset/closed, temporarily unavailable).\n* Uses `retry_after` when available, otherwise exponential backoff.\n* Markdown parse errors are not retried; they fall back to plain text.\n\nSet retry policy per provider in `~/.openclaw/openclaw.json`:\n\n* Retries apply per request (message send, media upload, reaction, poll, sticker).\n* Composite flows do not retry completed steps.",
|
|
"code_samples": [],
|
|
"headings": [
|
|
{
|
|
"level": "h2",
|
|
"text": "Goals",
|
|
"id": "goals"
|
|
},
|
|
{
|
|
"level": "h2",
|
|
"text": "Defaults",
|
|
"id": "defaults"
|
|
},
|
|
{
|
|
"level": "h2",
|
|
"text": "Behavior",
|
|
"id": "behavior"
|
|
},
|
|
{
|
|
"level": "h3",
|
|
"text": "Discord",
|
|
"id": "discord"
|
|
},
|
|
{
|
|
"level": "h3",
|
|
"text": "Telegram",
|
|
"id": "telegram"
|
|
},
|
|
{
|
|
"level": "h2",
|
|
"text": "Configuration",
|
|
"id": "configuration"
|
|
},
|
|
{
|
|
"level": "h2",
|
|
"text": "Notes",
|
|
"id": "notes"
|
|
}
|
|
],
|
|
"url": "llms-txt#retry-policy",
|
|
"links": []
|
|
} |