Re-add the claude-subscription LiteLLM route — confirmed working for the real CLI

Earlier this session I removed this route after a curl-based test got
rejected by Anthropic and concluded OAuth subscription forwarding doesn't
work through a proxy at all. That conclusion was wrong: the real `claude`
CLI binary, with ANTHROPIC_BASE_URL pointed at litellm, successfully
completed a request billed against the subscription. The earlier curl test
just didn't replicate whatever header/fingerprint Anthropic requires from
genuine Claude Code CLI traffic — LiteLLM relays that fine when the real
CLI is the caller, but a hand-built request from any other client (Hermes
included) still gets rejected the same way curl did.

litellm-config.yaml

@@ -11,13 +11,19 @@ model_list:
       model: openrouter/openai/gpt-4o-mini
       api_key: os.environ/OPENROUTER_API_KEY
 
-  # NOT included: a "claude-subscription" route forwarding the Claude Pro/Max OAuth token
+  # Routes to Anthropic using the CALLER's forwarded Authorization header (the Claude
-  # (from `claude setup-token`) through to Anthropic's raw API. Tested and confirmed
+  # Pro/Max subscription OAuth token) instead of a LiteLLM-held API key — billed against
-  # non-functional — Anthropic returns a generic rate_limit_error for ANY direct API call
+  # the subscription, not per-token. CONFIRMED WORKING, but only for the real `claude`
-  # using this token type outside the real Claude Code CLI client (reproduced with plain
+  # CLI binary as caller (tested: `claude -p` with ANTHROPIC_BASE_URL pointed here
-  # curl straight to api.anthropic.com, bypassing LiteLLM entirely, same result). The
+  # returned a real completion). An earlier test with plain curl replicating the same
-  # subscription token only works through the actual Claude Code CLI, which is what
+  # request shape failed — Anthropic apparently requires header/fingerprint details only
-  # claude-agent already uses directly for code tasks — it was never routed through here.
+  # the real CLI sends, which LiteLLM faithfully relays but a hand-built request won't
+  # have. Do NOT expect this to work for other callers (Hermes, generic HTTP clients) —
+  # they aren't the real CLI and can't reproduce that fingerprint.
+  - model_name: anthropic-claude
+    litellm_params:
+      model: anthropic/claude-sonnet-5
 
 general_settings:
+  forward_client_headers_to_llm_api: true
   master_key: os.environ/LITELLM_MASTER_KEY