mirror of
https://github.com/MoonshotAI/kimi-code.git
synced 2026-07-24 08:34:23 +00:00
* feat(retry): harden LLM API fault tolerance against 429/overload - retry more transient errors: 408/409/429/5xx/529, an embedded upstream status_code=429 in OpenAI Responses stream errors, and unclassified provider errors as a last-resort fallback - honor server Retry-After (parsed into APIStatusError.retryAfterMs by the OpenAI and Anthropic providers); chatWithRetry prefers it over its backoff - align app-level backoff with claude-code (500ms base, 32s cap, factor 2, up to 25% jitter) so high-attempt configs ride out multi-minute overload - emit a turn.step.retrying meta line in -p --output-format stream-json |
||
|---|---|---|
| .. | ||
| fixtures | ||
| abort.e2e.test.ts | ||
| api-shape.e2e.test.ts | ||
| error-paths.e2e.test.ts | ||
| events.e2e.test.ts | ||
| hooks.e2e.test.ts | ||
| retry.test.ts | ||
| streaming.e2e.test.ts | ||
| tool-args-parse.test.ts | ||
| tool-call.e2e.test.ts | ||
| tool-exchange-fallback.e2e.test.ts | ||
| tool-scheduler.test.ts | ||
| transcript.e2e.test.ts | ||
| turn-lifecycle.e2e.test.ts | ||