fix(nim): dynamically clamp max_tokens to resolve context window exhaustion (400 Bad Request) 3f2f05a Running dheraingoud commited on 8 days ago
fix(nim): classify expected context length / max context 400/500 errors as context_window_exceeded for automatic client compaction ea0ba58 dheraingoud commited on 8 days ago
feat: apply upstream commits f077c358, 8696e132, cb5b4305 7449374 dheraingoud commited on 10 days ago
Revert "fix(nim): handle progressive payload downgrades on NIM 500 internal server errors" de28646 dheraingoud commited on 13 days ago
fix(nim): handle progressive payload downgrades on NIM 500 internal server errors 4c86c77 dheraingoud commited on 13 days ago
fix(nim): pass body argument to _normalize_stream in KeyRotator loop to fix 502 error 036d875 dheraingoud commited on 13 days ago
feat: sync upstream 25th July commits (MiniMax-M3 native tool recovery, HTTP 403 permission denials) 00d1a83 dheraingoud commited on 13 days ago
feat: synchronize proxy with upstream commits up to 5305bd7 and integrate NIM key rotator 0a54372 dheraingoud commited on 17 days ago
fix(nim): limit rate-limit retries to number of keys to prevent hanging 38634b3 dheraingoud commited on 20 days ago
Fix: Bypass think_parser to emit raw thinking tags as plain text when reasoning isn't explicitly requested by client 8f93e8a dheraingoud commited on 21 days ago
Fix tight RateLimitError loop causing timeouts by sleeping when keys are cooling down ebea748 dheraingoud commited on 21 days ago
Deploy latest upstream with key rotation, vision adapter, and HF configs 61bb677 dheraingoud commited on 21 days ago
fix: next_client typo and dataclass super() issue in ExecutionFailure 9b65740 dheraingoud commited on 21 days ago
fix: implement missing _get_client methods for key rotation 130e8b3 dheraingoud commited on 21 days ago
fix: change timeout_s to http_read_timeout in Nim Provider initialization ee0e2b0 dheraingoud commited on 21 days ago