Update NVIDIA NIM models - keep top 5, add minimax-m2.7

Fix Silicon Flow model IDs with correct API names

Keep only 5 best Silicon Flow models for free tier

Add high-rate-limit Silicon Flow models for free tier usage

Add routing debug log to trace provider resolution.

$(cat <<EOF

$(cat <<EOF

$(cat <<EOF

Add Cerebras and Silicon Flow models to REQUESTED_PROVIDER_MODELS

Add Cerebras and Silicon Flow provider support

Extend session visibility in admin dashboard with configurable retention

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

Track sessions via X-Session-ID header for accurate admin dashboard

Add free Zen models: big-pickle, ring-2.6-1t-free, nemotron-3-super-free

Speed up NIM provider with failure tracking and faster timeouts

Speed optimizations and enhanced auto-model fallback routing

Performance optimizations for faster proxy routing

Display admin dashboard on root page

Track sessions by gateway client IP

Fix: use sync version of track_request to avoid SyntaxError

Fix: sessions tracking now works correctly in dashboard and JSON

Add admin dashboard for session monitoring

Add smart task-aware routing (Phase 1)

Performance optimizations for proxy speed and shared sessions

Remove groq/cerebras, add zen model

Deploy claude-code-nvidia proxy to Hugging Face Spaces