feat(error-handling): implement LLM error adaptation and classification for chat streaming

- Introduced LLMErrorCategory and adapt_llm_exception to normalize LLM exceptions.
- Updated llm_retryable_message and llm_permanent_message to utilize the new adaptation logic.
- Enhanced classify_stream_exception to classify provider errors and return user-friendly messages.
- Added tests for error classification and adaptation to ensure robustness.
- Updated frontend error handling to display appropriate messages based on new classifications.
This commit is contained in:
Anish Sarkar 2026-06-12 05:03:14 +05:30
parent 203ef78346
commit 8e8cf96faa
9 changed files with 533 additions and 38 deletions

View file

@ -91,6 +91,10 @@ export function tagPreAcceptSendFailure(error: unknown): unknown {
"TURN_CANCELLING",
"AUTH_EXPIRED",
"UNAUTHORIZED",
"MODEL_AUTH_FAILED",
"MODEL_NOT_FOUND",
"MODEL_CONTEXT_LIMIT",
"MODEL_PROVIDER_UNAVAILABLE",
"RATE_LIMITED",
"NETWORK_ERROR",
"STREAM_PARSE_ERROR",