Model Retry Strategy
✅Solved
Is this a valid configuration for a model retry strategy for when models return errors?
{
"agents": {
"defaults": {
"model": {
"retryConfig": {
"maxAttempts": 5,
"initialDelayMs": 1000,
"backoffMultiplier": 2.5,
"retryableStatuses": [429, 402, 503]
}
}
}
}
}
{
"agents": {
"defaults": {
"model": {
"retryConfig": {
"maxAttempts": 5,
"initialDelayMs": 1000,
"backoffMultiplier": 2.5,
"retryableStatuses": [429, 402, 503]
}
}
}
}
}
Solution
Yes — the model can be changed mid-session, and the next turn will use the new model while keeping the same conversation context/history.
Typical flow:
1.
2. (keep chatting normally…)
3.
4. next message uses 2.5-flash
A couple important Discord nuances:
- If you’re using Discord native slash commands (the autocomplete UI), OpenClaw runs those in an isolated “slash session” on Discord. So a
- If you want
Typical flow:
1.
/model google-vertex/gemini-3-flash-preview2. (keep chatting normally…)
3.
/model google-vertex/gemini-2.5-flash4. next message uses 2.5-flash
A couple important Discord nuances:
- If you’re using Discord native slash commands (the autocomplete UI), OpenClaw runs those in an isolated “slash session” on Discord. So a
/model …- If you want
/model
The AI that actually does things. Emails, calendar, home automation - all from your favorite chat app. New shell, ready to help. The lobster way.
131,281Members
Resources
Recent Announcements
Similar Threads
Was this page helpful?
