LLM automatic retry setting card
zeng6125-rgb/dsh-llm-retry-settings · model-adapters
DSH plug-in: LLM automatic retry setting card - the adjustment of the number of retries and backoff time takes effect in real time, and additional retryable error codes can be checked (INVALIDREQUEST is added by default.
★ 4GitHub stars
0Forks
2026-08-26Last updated
JavaScriptLanguage
MITLicense
Key features
- Includes the settings UI (client bundle lib/client.js): a card in Settings → General — no separate UI package needed.
- Overrides maxRetries, initialDelayMs, maxDelayMs, and jitterRatio on the agent/request-error retry policy.
- New in 0.1.3 — configurable retryableCodes: extra failure codes to retry on, merged into each provider's own list (never replaces it).
- Defaults to INVALID_REQUEST + PI_AI_ERROR, so OpenAI-style HTTP 400 errors (thinking-mode reasoning_text) and generic stream failures get retried out of the box.
- Default enabledfalse = fully bypassed
Install command
dsh plugin --profile web add github:zeng6125-rgb/dsh-llm-retry-settings