Better handle rate limit errors that come as 413 or BadRequestError.

Add detailed error mapping debug logs.

Add credential logging at provider creation.

Add detailed error logging to trace API failures.

Add Cerebras, Silicon Flow, and Groq providers with debug logging.

$(cat <<EOF

$(cat <<EOF

$(cat <<EOF

$(cat <<EOF

Add Cerebras and Silicon Flow provider support

Implement image support in proxy with vision-aware routing

NIM speed optimization — adaptive rate limiting and increased throughput

Fix stale sessions in admin dashboard and improve auto-routing health

Optimize auto routing: Zen unlimited, smarter fallback skipping

Speed up NIM provider with failure tracking and faster timeouts

Speed optimizations and enhanced auto-model fallback routing

Fix: sessions tracking now works correctly in dashboard and JSON

Fix httpx keepalive_expiry parameter name

Performance optimizations for proxy speed and shared sessions

Remove groq/cerebras, add zen model

Deploy claude-code-nvidia proxy to Hugging Face Spaces