docs: update CLAUDE.md with auto-routing optimizations

- Zen unlimited rate limit (9999 req/min)
- Silent blocked-skip for NIM providers
- Load-based candidate ordering
- Session tracking via X-Session-ID header
- Fix AUTO_MODEL_PRIORITY -> AUTO_MODEL_ORDER

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

CLAUDE.md

@@ -53,10 +53,12 @@ Claude Code CLI → api/routes.py (FastAPI) → api/model_router.py → provider
 
 ### Auto-Routing with Health Tracking
 The proxy includes intelligent model selection:
-1. Pre-flight health check (recent failures in 30s window)
+1. Pre-flight health check (recent failures in 30s window per model)
 2. Skip unhealthy models (3+ failures = unhealthy for 30s)
 3. Automatic failover on timeout/rate-limit
-4. 40 req/min rate limit respected
+4. Zen provider is unlimited (9999 req/min scoped limiter) — never blocked by rate limits
+5. Blocked NIM providers skipped silently (no failure penalty)
+6. Load-based ordering — least-loaded providers tried first
 
 ### Key Modules
 
@@ -83,7 +85,10 @@ The `except X, Y:` syntax is valid in Python 3.14 (reintroduced). Do not moderni
 
 Key variables in `.env`:
 - `MODEL` — Primary model (e.g., `zen/minimax-m2.5-free`)
-- `AUTO_MODEL_PRIORITY` — Comma-separated fallback order
+- `AUTO_MODEL_ORDER` — Comma-separated fallback order for auto routing
 - `NVIDIA_NIM_API_KEY` — NVIDIA API key
 - `ANTHROPIC_AUTH_TOKEN` — Auth token (any secret)
-- `ENABLE_MODEL_THINKING` — Enable reasoning blocks
+- `ENABLE_MODEL_THINKING` — Enable reasoning blocks
+
+### Session Tracking
+Start Claude Code with `--session-id <uuid>` so the admin dashboard shows accurate per-session metrics. The proxy reads the `X-Session-ID` header for session identification.