Unverified50% confidenceFactExact time
llm-retry's default retry_on_http_codes list does not include 529 (overloaded_error) and 408 (request timeout), causing these errors to never be retried.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/19/2026
First Seen
Valid until: 1/17/2027
Sources
Related Entities
Related Claims
UnverifiedIn LLM calls, client errors such as 400 (malformed request) and 401 (invalid key) should not trigger switching to a backup provider, because resending will only get the same error; only transient provider-side failures such as connection failures, timeouts, 429, and 5xx should trigger fallback.75% similarUnverifiedRetries for free APIs should only target transient errors such as 429 and 503; other errors should be thrown directly to avoid blindly retrying code bugs.69% similarUnverifiedAfter setting DFLASH_TOKENS=15, in citation requests with a 20k context it causes the engine to crash, reporting EngineDeadError and a marlin_gemm allocation failure, after which every request returns 500 and it cannot self-recover.67% similarUnverifiedError responses (such as 429 or 5xx) should never be cached, so that the next call can retry.65% similarUnverifiedThis version fixes an issue where excessively large failure output from background tasks caused API request bodies to exceed size limits and fail65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1064751API
curl https://kongchang.com/api/v1/knowledge/claims/1064751MCP
get_claim(id=1064751)